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

Beyond the readOnly/idempotent/destructive annotations, the description reveals the connection reuse model, no-new-OAuth behavior, limited result fields, inability to mutate, cost, and a hallucination guard ('Never invent email contents'). 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?

The description is dense but front-loaded: purpose first, then auth, query guidance, return shape, and routing in logical order. Every sentence carries distinct operational information, and the cost/auth line is concise at the end.

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 output schema and annotations, this is complete: it covers prerequisites (connection/API key), behavioral limits, result scope, follow-up path, and failure guidance. An agent has everything needed to select and invoke it correctly.

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 coverage is 100%, so the baseline is 3; the description adds useful query syntax guidance with operators like from:, is:unread, newer_than:7d, and has:attachment. It does not repeat parameter names but complements the schema's examples.

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 states a specific verb ('Search'), resource ('the authenticated user's already-connected Gmail inbox'), and mode ('read-only'), and explicitly scopes the return value to metadata fields without body. It also distinguishes itself from the sibling read_gmail_message by directing follow-up there.

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?

It gives concrete when-to-use context: prefer Gmail operators, follow up with read_gmail_message for bodies, and clearly excludes send/archive/delete. It also provides setup guidance for unconnected Gmail and states auth restrictions (API key/OAuth vs share tokens).

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