search

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

With no annotations provided, the description carries the full burden of behavioral disclosure, and it does this thoroughly. It reveals mode internals (cosine similarity vs. hybrid rank combination), preservation of recall's priorities and filters, the limitation that 'Ranking cannot promote evidence', and operational constraints including that 'search itself never downloads models or uses hosted inference'. This is far beyond a typical minimal 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 compact and front-loaded with the main purpose, then gives essential behavioral and operational details. Every sentence contributes value, though the middle section is a dense block of clauses that could be slightly better structured with bullet points or clearer separation between features and prerequisites.

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 search tool with four parameters and no output schema, the description provides enough operational context to invoke it correctly: mode behavior, preserved filter rules, ranking constraints, and prerequisites. The main gap is that it does not describe the return shape or how results are ordered, which would be useful since no output schema exists.

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 compensate for the schema's lack of parameter documentation. It adds real meaning to 'mode' by explaining 'semantic' and 'hybrid', and it references the 'global limit' and 'frame filter', giving context to 'limit' and 'frame'. The 'query' parameter itself is self-evident. Coverage is strong but does not exhaustively document every parameter's allowed values or formats.

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 the tool's purpose with a specific verb and resource: 'Find paraphrased evidence'. It also names the core search mode distinction, which helps distinguish it from a plain lexical recall. However, it does not explicitly differentiate itself from sibling tools like 'recall', relying on implication rather than naming alternatives.

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 implies usage for paraphrased/semantic evidence search and explicitly mentions prerequisites ('Requires the semantic extra and explicit model download beforehand'). It does not clearly state when to use this tool versus alternatives such as 'recall', nor does it provide exclusions or when-not-to-use conditions, leaving the selection logic partially inferred.

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