search_cached_models

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

No annotations are provided, so the description bears full responsibility for behavioral disclosure. It only states the tool 'searches' the local cache, implying a read-only, safe operation, but does not explicitly confirm non-destructiveness, specify authorization requirements, or mention any side effects. With no annotation support, the description is insufficient.

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, with the core purpose in a single sentence followed by a structured argument list. It is front-loaded and easy to scan. No superfluous words. Could be slightly more compact by integrating argument descriptions into the main sentence, but overall it's efficient.

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?

For a basic search tool with 4 parameters and no output schema, the description covers input semantics adequately but omits output format, pagination behavior (beyond the limit default), and expected response shape. With no annotations, the agent lacks information about result ordering, total count, or empty result handling. Adequate but has clear gaps.

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 description coverage is 0%, so the description compensates well by explaining parameter semantics. 'query' is clarified as free-text search against file name, prompt, and tags. 'source' has an example ('"thingiverse"'). 'tags' is described as comma-separated. 'limit' notes default 20. These add non-trivial meaning beyond the schema types. Minor gap: no format constraints or valid values for source.

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 'Search the local model cache' with specific filter dimensions (name, source, tags, prompt text). This distinguishes it from sibling tools like search_models (broader) and search_all_models (different scope). The verb 'search' and resource 'local model cache' are specific and unambiguous.

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?

No guidance on when to use this tool versus alternatives (e.g., search_models, search_all_models). The description does not specify prerequisites, context, or situations where this tool should be avoided. The user must infer usage purely from the tool name and minimal description.

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