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

Annotations already declare readOnlyHint=true, openWorldHint=true and destructiveHint=false, so the safety profile is covered. The description adds real value beyond that by specifying the result granularity ('metadata and snippets', not full bodies). It is silent on pagination behavior despite a pageToken parameter existing.

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?

Two short sentences, zero filler, with the positive capability stated before the exclusions. Nothing needs to be trimmed and nothing is buried.

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 five-parameter, paginated search tool with no output schema, the description usefully characterizes the return payload but omits the parameter semantics that the schema leaves undocumented. Adequate but with a clear gap around the account-selection and paging parameters.

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 only 20% – just 'query' is documented. The description hints that an inbox must be selected ('one inbox') but never explains emailAddress vs emailAccountId, maxResults (capped at 20), or pageToken. With four undocumented parameters, the description does not compensate for the coverage gap.

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 one inbox') plus the return shape ('message metadata and snippets'), and scopes the resource with 'one'. It implicitly separates itself from read_mail by denying full bodies, but never names a sibling alternative explicitly.

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 negative clauses ('Does not return full message bodies, send email, or change mail') effectively route the agent away from read_mail, send_mail and change_mail, which is genuine when-not guidance. It does not, however, state when this tool is the right choice over browse_mail or how to pick the target inbox.

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