Search documents

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, and the description adds meaningful behavior beyond them: it returns a compact per-document summary and deliberately omits full OCR text to avoid flooding context. This is useful operational context for an agent deciding whether the result will fit the conversation.

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?

Three sentences with no filler. The core purpose, expected return shape, and the key alternative (get_document_content) are all present and front-loaded.

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 23-parameter tool with no output schema, the description covers the essential selection information: search modes, response summary structure, and the alternate tool for full text. Filtering and pagination details are carried by the schema, and the enumerated summary fields compensate for the missing output schema.

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 96%, so the schema already documents nearly every parameter; the baseline of 3 applies. The tool description adds a high-level statement about full-text and metadata filters but does not need to repeat individual parameter details.

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 action ('Find documents') plus the two search modes (full-text and metadata filters), so the resource and operation are unambiguous. It also distinguishes itself from get_document_content by noting it returns summaries, not OCR text. The 'main entry point for every "which documents..." question' framing makes the purpose immediately usable.

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 clearly tells the agent this is the default for document-finding questions and explicitly points to get_document_content when OCR text is needed. It does not contrast with sibling tools like global_search or search_autocomplete, so some alternative routing remains implicit.

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