Search file contents

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

Goes well past the readOnly/idempotent annotations: it discloses the all-words-must-match rule, BM25 ranking, wildcard behavior, index staleness with a stale:true flag, and that the Drive listing is not rechecked. The explicit warning that snippets are untrusted file content adds a safety-relevant behavior an agent could not infer from any structured field.

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?

Dense but front-loaded: purpose first, then prerequisite, then query semantics, then return shape and freshness, closing with a safety note. Every clause carries information an agent needs and none is redundant with the schema or annotations.

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?

Despite having no output schema, the description spells out the return shape ({path, score, snippet, indexedAt}) and the staleness caveat. Combined with the prerequisite and the injection warning, an agent has everything needed to call this correctly and interpret results.

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 100%, so the schema already documents path, limit, and query. The description does add query semantics beyond the schema (all words must match, trailing * prefix expansion, BM25 ordering), which is genuine value, but it says nothing additional about the path or limit parameters.

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 the text of files") and immediately restricts scope to files indexed by drive_content_index, which separates it from the filename-oriented drive_search sibling. The required env var and index dependency are front-loaded rather than buried.

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?

Gives a clear precondition (files must be indexed, PROTON_DRIVE_CONTENT_INDEX=1) so an agent knows when this tool can work at all. It stops short of naming drive_search as the alternative for filename lookups or stating when-not-to-use, leaving that inference to the agent.

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