search_api

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds the query semantics and the 1-20 limit bound, but says nothing about ranking behavior, whether results are paginated, or what a result contains, which matters for a search tool with no output schema.

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 core purpose is front-loaded in the first sentence with examples, and the Args block is compact. The Args section partially duplicates the schema property names, but given 0% schema description coverage it earns its place as the compensating documentation.

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 3-parameter discovery tool with no output schema, the description covers inputs well but leaves the result shape unspecified (names only? signatures? snippets?) and does not indicate the follow-up workflow to get_api_card. It is callable as-is but not fully self-contained.

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 carry the load, and it does document all three parameters: query as 'what the code needs to do, or part of a function name', library as an optional prefix filter with concrete prefix examples ('cupy', 'cupyx.scipy.sparse', 'nvmath'), and limit as max results 1-20 (a bound the schema does not state). It stops short of describing the matching/ranking semantics that would fully disambiguate vague queries.

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?

States a specific verb and resource ('Search CuPy / nvmath-python APIs') and scopes the covered libraries (cuBLAS, cuFFT, cuSOLVER, cuSPARSE, cuDSS, cuTENSOR) with concrete query examples. An agent can distinguish it from get_api_card/get_example by the 'search by task description' framing, though it never explicitly contrasts itself with those siblings.

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?

Usage is implied through examples ('batched least squares', 'rfft') and the library-prefix filter, which show the intended input style. However, there is no explicit when-to-use/when-not guidance, e.g. that this is the discovery step before get_api_card, or when to prefer an exact-name lookup over a task-description search.

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