semantic_search

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

No annotations, so description carries full burden. Discloses return fields (file, page_start/end, score, text), score interpretation (cosine, higher=closer), and critical limitation that fragments are not verbatim and must be verified.

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 paragraphs with bold, bullet-like structure. First sentence front-loads purpose, warning is clearly separated. Every sentence adds value.

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 output schema exists, description adds value by explaining return semantics and limitations. Covers purpose, usage, parameters briefly, and behavioral traits. No 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 coverage is 0%, so description must compensate. It explains 'k' as 'top-k' and 'query' implicitly, adding context beyond bare schema. Could explicitly state k is number of fragments, but sufficient.

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?

Clearly states 'retrieve text-layer passages by *meaning*', distinguishing from keyword grep. Specific verb and resource, and contrasts with sibling 'semantic_search_info' (though not detailed).

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?

Explicitly says it catches what 'keyword grep misses', implying when to use it. Provides a warning about recall layer and citation limitations, but does not explicitly contrast with 'semantic_search_info'.

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