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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, making safety clear. The description adds useful behavioral context: it validates against a 'draft-07 subset' and lists supported keywords, which helps the agent understand limitations. However, it does not disclose performance considerations (e.g., large schemas) or error handling beyond returning errors with dot-notation paths.

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 concise (two sentences) and front-loaded with the core purpose. The second sentence lists supported features efficiently. It could be slightly more structured (e.g., bullet points) but is clear and free of fluff.

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?

Given the tool's moderate complexity (2 params, draft-07 subset) and the presence of an output schema, the description covers the key validation features and return format. It does not mention edge cases (e.g., cyclic schemas) or how to handle unknowns, but the annotations and schema provide sufficient context.

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?

Schema coverage is 100%, so parameters are fully described in the schema itself. The description adds minimal extra semantic meaning—only noting that value and schema can be JSON strings or objects. The return value format is covered by an output schema, so no additional param info is needed.

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 tool name 'json_schema_validate' is descriptive, and the description explicitly states 'Validate a JSON value against a JSON Schema (draft-07 subset)'. This clearly distinguishes it from siblings like json_schema_generate or json_diff, which serve different purposes.

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 mentions the supported schema features (e.g., type, required, properties) but does not provide explicit guidance on when to use this tool versus alternatives like llm_json_schema_check or function_call_validate. There is no mention of when not to use it or prerequisites.

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