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

Annotations already declare readOnlyHint=true, destructiveHint=false, openWorldHint=false, so the safety profile is covered. The description adds genuine context beyond that: the minimum-one-filter validation rule (not expressed in the schema, whose only required field is mailbox) and the fact that free text covers headers and body. It stops short of describing result limits or pagination.

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?

Three tight sentences: purpose and filter dimensions first, the binding constraint second, the return shape last. No filler, nothing redundant, and the most actionable rule (at least one filter) is not 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?

With 10 parameters, no output schema, and no annotations covering results, the description does the necessary work by stating it returns message summaries with uids and by stating the filter requirement. It omits any mention of result caps, sorting, or pagination, which an agent paging through a large folder would want.

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 every parameter is already documented in the schema. The description's filter enumeration (from, to, subject, body, date range, attachments) mostly mirrors the schema fields, though it usefully clarifies that 'q' spans headers and body. Baseline 3 is appropriate when the schema does the heavy lifting.

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 (Search) and resource (messages) and scopes it to 'a mailbox folder', enumerating the filter dimensions (from, to, subject, body, date range, attachments). It implicitly separates itself from list_messages and search_all_mailboxes via the folder scoping, but never names a sibling to sharpen the distinction.

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?

Provides one real usage rule – 'At least one filter is required' – which tells the agent when this tool is applicable versus an unfiltered browse. However, it gives no explicit guidance on when to prefer it over list_messages or search_all_mailboxes; the routing must be inferred.

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