search

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

Discloses read-only nature (SIDE EFFECTS: none, annotations readOnlyHint true), re-verification of labels, and pagination. No contradiction with annotations.

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?

Concise yet comprehensive: first sentence defines, then details, usage guidance, side effects. No wasted words.

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?

Covers purpose, usage, behavior, pagination, and side effects. Given output schema exists, return values need not be detailed. Complete for its complexity.

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?

Despite 0% schema coverage, description explains query parameter via example, pageToken for pagination. Does not explicitly mention maxResults or its constraints, but context implies it. Good but slightly incomplete.

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?

Description clearly states 'Search Gmail with native query syntax' and specifies returns thread summaries. Distinguishes from sibling tool get_thread by stating not to use for threads already identified.

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 provides USE WHEN conditions (locating threads by sender, subject, etc.) and DO NOT USE with an alternative (use get_thread). Also explains pagination with nextPageToken and pageToken.

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