similar_patents

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

With no annotations, the description carries the full burden and does substantial work: it discloses the ranking algorithm (FTS5 bm25), the fields scored, the valid n range, and the returned metadata fields. The closing caveat that this is 'a record of what the corpus contained, not a search opinion' sets useful expectations about result nature and recall limits. What is missing is any note on latency, corpus scope beyond 'US', or how ties or short inputs are handled.

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?

Two sentences, front-loaded with the operation and count, then the method, then the caveat. Dense but every clause carries information. The unexplained jargon 'FTS5 bm25' costs a little clarity for an agent unfamiliar with the ranking backend.

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?

An output schema exists, so return values need not be spelled out, and the tool is simple at two parameters. Still, for a tool whose only input semantics hinge on how text is formatted, the definition leaves that ambiguous, and it never clarifies how this relates to search_patents in the same family.

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 supply parameter meaning, and it only partly does. It usefully constrains n to 1-20 (the schema shows only a default of 20) and implies the text parameter should be a title plus abstract, but it never says whether that is a concatenated string, whether a delimiter is expected, or what happens if only a title is supplied.

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 names a concrete operation (return the n nearest US patents to a supplied title-plus-abstract), the retrieval method (FTS5 bm25 over title and abstract), and the return payload (data_version, as_of). It does not explicitly distinguish itself from the sibling search_patents, so an agent must infer that this one is similarity-ranked rather than a keyword search, but the core purpose is 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?

Usage is implied by the phrase 'nearest to a title plus abstract' and by the caveat that results are a corpus record rather than a search opinion, which hints at when to prefer it. However, there is no explicit when-to-use guidance, no statement of when not to use it, and no named alternative such as search_patents despite that sibling being the obvious point of confusion.

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