agentleFS
Wsh7AshWsh7Ash/skillmcp/skills/tools-list-schema-validation/SKILL.md

tools-list-schema-validation

Skill0 starsChanged 14 days agoMITView on GitHub

Validate every advertised schema as JSON Schema before a client tries to obey it. Use when a tool's input schema was edited and clients construct arguments from it

The file

We split this skill into the rules it gives an agent

10 rules. About 0 are common, 10 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈10

    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
  1. Distinctive:

    Read tools/list output and collect every inputSchema

    line 20
  2. Distinctive:

    Check each schema is an object with type object and a properties map

    line 21
  3. Distinctive:

    Check required names exist in properties

    line 22
  4. Distinctive:

    Check enums are non-empty and defaults satisfy their own constraints

    line 23
  5. Distinctive:

    Check additionalProperties is explicitly false where strictness is intended

    line 24
  6. Distinctive:

    Add the checks to the test suite so a schema edit cannot regress

    line 25
  7. Distinctive:

    no required key is missing from properties

    line 29
  8. Distinctive:

    every enum has at least one value

    line 30
  9. Distinctive:

    no default value violates its own bounds

    line 31
  10. Distinctive:

    every advertised schema passes the structural checks

    line 62

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Tools List Schema Validation

Validate every advertised schema as JSON Schema before a client tries to obey it

Use when: a tool's input schema was edited and clients construct arguments from it

Avoid when: the tool takes no arguments and its schema is a constant empty object

Procedure

  1. Read tools/list output and collect every inputSchema
  2. Check each schema is an object with type object and a properties map
  3. Check required names exist in properties
  4. Check enums are non-empty and defaults satisfy their own constraints
  5. Check additionalProperties is explicitly false where strictness is intended
  6. Add the checks to the test suite so a schema edit cannot regress

Signals

  • no required key is missing from properties
  • every enum has at least one value
  • no default value violates its own bounds
  • strict tools declare additionalProperties false

Patterns

1. Required check

set(schema['required']) <= set(schema['properties'])

2. Bounds check

1 <= default <= maximum

3. Strictness

additionalProperties is False, not absent

Pitfalls

  • Assuming a client validates the schema and finding out it does not
  • Leaving a default outside its own min or max
  • Declaring required keys that the handler treats as optional

Done when

  • every advertised schema passes the structural checks
  • the checks run in CI on every change

References

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.