Search Images

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

With no annotations provided, the description carries the full burden, and it does so thoroughly. It discloses the ranking mechanism, the auto fallback threshold, what each provider does, and the exact result signals: 0-100 text score, domain hint, and explainable signals. It even tells the agent how to assess confidence and when verification is needed, which goes well beyond a minimal tool description.

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 front-loaded with purpose and behavior, and the Args section is logically organized. It is longer than typical descriptions, but that length is justified by the zero-coverage schema and the need to explain provider behavior and scoring. Minor redundancy exists because provider defaults and enum values are repeated from the schema, but the added context still earns its place.

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 provider-switching complexity, fallback threshold, scoring semantics, and four parameters, the description provides everything needed to select and invoke it correctly. It explains query formulation, ranking confidence, provider differences, and optional verification workflow. The output schema covers return structure, so the description does not need to detail the exact JSON response.

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 must fully compensate for the schema's lack of parameter documentation. It does: `query` has concrete examples and wording advice ('复旦光华楼' is better than '光华楼'), `count` is bounded 1-20, `market` is explained as locale-specific to Bing while Commons is language-neutral, and `provider` enumerates the options. This is excellent parameter documentation.

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 opens with a specific verb and resource: 'Search image indexes and rank results with pure text so vision is not required.' This clearly distinguishes the tool from the sibling `search`, `open`, and `find` by emphasizing image indexes and text-based ranking. The provider variants (bing_images, commons) further specify exactly what kind of image search this is.

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 usable routing guidance: `auto` is the default, it falls back to Commons below ~40 text score, and results below ~40 should be treated as unverified. It also recommends verifying with `find`/`open` before downloading, which indirectly differentiates this search tool from sibling file/URL tools. It lacks an explicit 'when not to use this tool' statement, but the behavioral and provider guidance is clear enough.

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