search

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

The description goes far beyond the readOnlyHint annotation, disclosing that spam/trash are excluded unless named, that pages can be short with a nextPageToken, that signals are derived from headers, and that no hits may mean 'none outside spam/trash'. It also explicitly states 'SIDE EFFECTS: none', aligning with readOnlyHint. No contradiction.

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 long but every sentence earns its place, covering critical behavioral nuances. It is front-loaded with the core purpose and query syntax, then dives into pagination and spam/trash caveats. The USE WHEN/DO NOT USE structure aids scannability. Slightly verbose but justified by the complexity.

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 the tool's complexity (pagination, spam/trash exclusion, signals derivation, false positives), the description is remarkably complete. It covers return values (signals, nextPageToken), edge cases (short pages, spam), and usage guidance. The output schema exists, so return format details are not needed in the description.

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. It explains the query parameter with examples and describes the pageToken behavior and maxResults pagination semantics. It doesn't detail maxResults bounds (schema has that), but it adds crucial context about short pages and nextPageToken, which is more valuable than repeating schema constraints.

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 searches Gmail with native query syntax and returns thread summaries. It distinguishes itself from siblings by explicitly noting it is for locating threads by sender, subject, date, label, or read state, and not for fetching a thread by ID (which is get_thread's job).

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 provides explicit 'USE WHEN' and 'DO NOT USE' sections, naming the alternative tool (get_thread) and clarifying when not to use this tool. It also gives detailed guidance on handling spam/trash exclusions and pagination, which are critical usage contexts.

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