ag_json_validate

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description fully carries the burden and discloses key behaviors: 'Deterministic, fixture-verified', 'free for guests (rate-limited; pass your Guild api_key to use your member budget)', error cap of 50, and the inclusion of a 'Guild-signed provenance envelope' in the response. This provides substantial transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is slightly verbose, with three paragraphs including promotional phrases like 'Deterministic, fixture-verified' and 'Guild-signed provenance envelope', but it is still well-structured and directly relevant. The length is acceptable for the amount of transparency it provides.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers the tool's purpose, output, error cap, and auth nuances, but omits the structure of the payload input. It also mentions a provenance envelope not reflected in the output schema, which could confuse agents expecting a strict match. Overall, it is partially complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema only defines api_key and payload, but the description does not clarify the expected payload structure (e.g., that it should contain both 'instance' and 'schema' fields). It mentions 'caller-supplied JSON Schema' and 'JSON instance' but never maps these to the payload parameter, leaving a significant gap for the caller.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Validate' and the resource 'a JSON instance against a JSON Schema (draft 2020-12)', along with a specific outcome ('returns structured errors (path + message), capped at 50'). This is specific enough to distinguish it from sibling tools like ag_json_repair or ag_json_schema_infer.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives a concrete use case ('Use before passing data across an agent boundary') but does not explicitly contrast with alternative tools such as ag_json_repair or ag_json_schema_infer, nor does it provide conditions for when not to use this tool. Guidance is present but limited.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.