search_messages

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

With zero annotations the description carries the full burden and mostly delivers: substring vs. header/body scope, attachment exclusion, date format with exclusive 'before', newest-first ordering, a hard cap of 100 results, and the UID handoff to get_message/get_thread. Gaps remain on error behavior for a nonexistent folder and on whether folder names are case/path-sensitive (needed since list_folders is the sibling).

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?

Front-loaded with the core action, then a compact filter-by-filter gloss that maps to the parameter list. No filler sentences; every clause either scopes behavior or defines a parameter.

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 9-parameter, annotation-free, no-output-schema search tool, the description covers filter semantics, result ordering, result cap, and the follow-up UID usage – enough to call it correctly. The only substantive omission is unread_only, which is a minor gap against an otherwise complete picture.

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 0%, so the description must compensate and largely does: text/sender/recipient/subject matching semantics (including recipient covering To and Cc), since/before formats and exclusivity, and limit's max and ordering. However, `unread_only` is never mentioned and the `folder` parameter's accepted values are undefined beyond 'one folder'.

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?

Opens with a specific verb+resource: 'Search one folder', which immediately distinguishes it from the ID-based siblings (get_message, get_thread, get_attachment_text) and from create_draft. It doesn't explicitly name those siblings as alternatives, but the role is unmistakable.

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?

'Search one folder' implies the tool is non-recursive and must be re-called per folder, and 'All filters are combined with AND' tells the agent how to compose filters. The note that the server does NOT search inside attachments effectively redirects to get_attachment_text, though that alternative is never named explicitly.

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