tool-verb-naming
Skill0 starsChanged 15 days agoMITView on GitHub
Name tools after the action they perform so a model chooses correctly from the name alone. Use when a new tool is being added and the name is still free-form
In this repository49 other files it gives its agents.
- argument-construction-from-artifactsSkill
- audit-log-of-tool-callsSkill
- bounded-output-designSkill
- capability-negotiation-checkSkill
- changelog-and-versioningSkill
- concurrency-and-ordering-checkSkill
- context-window-managementSkill
- credential-isolationSkill
- data-retention-policySkill
- description-as-contractSkill
- destructive-action-confirmationSkill
- destructive-tool-gatingSkill
- deterministic-command-choicesSkill
- done-when-criteriaSkill
- error-shape-for-agentsSkill
- fixture-driven-transcript-testsSkill
- human-in-the-loop-escalationSkill
- idempotency-annotationSkill
- input-schema-strictnessSkill
- least-privilege-tool-grantsSkill
- lifecycle-test-initialize-then-toolsSkill
- local-vs-remote-boundarySkill
- one-procedure-per-skillSkill
- pagination-and-limit-disciplineSkill
- parallel-tool-call-safetySkill
- protocol-conformance-testSkill
- protocol-version-handshakeSkill
- publishing-a-pack-locallySkill
- rate-limit-respectSkill
- reference-canonicalisationSkill
- replay-transcript-for-regressionSkill
- restart-and-reload-semanticsSkill
- scope-guard-before-executionSkill
- search-then-fetch-patternSkill
- secrets-via-environmentSkill
- server-discovery-and-trustSkill
- signal-and-pitfall-sectionsSkill
- skill-frontmatter-contractSkill
- stdio-client-configSkill
- stdout-purity-checkSkill
- third-party-server-sandboxingSkill
- tool-call-budgetingSkill
- tool-call-error-pathsSkill
- tool-error-without-retry-stormSkill
- tools-list-schema-validationSkill
- tool-surface-minimisationSkill
- transport-choiceSkill
- verify-tool-output-before-reportingSkill
- when-to-use-and-avoidSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 20
Write the one sentence the tool performs, in verb-first form
- Distinctive: line 22
Check the name against existing tools for collisions and near-duplicates
- Distinctive: line 23
Avoid generic verbs such as run, do, execute or process
- Distinctive: line 24
Put the distinguishing detail in the description, not the name
- Distinctive: line 30
no two tools differ only by a suffix
- Distinctive: line 62
every tool name is verb-first and unique
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Tool Verb Naming
Name tools after the action they perform so a model chooses correctly from the name alone
Use when: a new tool is being added and the name is still free-form
Avoid when: the server exposes one tool and naming ambiguity cannot arise
Procedure
- Write the one sentence the tool performs, in verb-first form
- Derive the name from that verb and its object, in snake_case
- Check the name against existing tools for collisions and near-duplicates
- Avoid generic verbs such as run, do, execute or process
- Put the distinguishing detail in the description, not the name
- Re-read the final name as a model would, with no other context
Signals
- the name states what happens, such as get_skill or search_skills
- no two tools differ only by a suffix
- the description adds constraints rather than repeating the name
- a reader can predict the return shape from the name
Patterns
1. Verb object
search_skills, get_skill, list_packs2. Avoided names
run_task, do_thing, execute_action3. Distinct pair
search_skills versus get_skill: one query, one fetchPitfalls
- Naming a tool after its implementation, such as index_lookup
- Two tools whose names differ only by a word the model cannot see the effect of
- Encoding prerequisites in the name instead of the schema
Done when
- every tool name is verb-first and unique
- each name's return shape is guessable before reading the schema
References
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

