Search mail

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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds genuinely non-obvious behavior: `full_text` only hits the already-indexed set, substring filters are evaluated per folder, dates are ISO-8601, results are summaries not full messages, and a first page carries `scope` so empty results can be interpreted. That is real disclosure beyond structured fields, though it omits rate/latency or index-coverage caveats.

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 short paragraphs, front-loaded with the primary distinction between search modes, followed by format, pagination, and return-summary notes. Every sentence carries information an agent needs; nothing is restated from the schema or annotations.

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 22-parameter tool with an output schema and full annotation coverage, the description supplies the operational essentials: how the two matching modes differ, date format, result granularity, pagination, and the follow-up call for message bodies. The remaining shortfall is the undocumented filter parameters, which no other field compensates for.

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 0% across 22 parameters, so the description carries the full burden and only covers roughly five of them (`full_text`, `subject`, `author`, `body`, dates, `cursor`). The index-vs-substring distinction for those fields is valuable, but filters like `tag_mode`, `min_size`/`max_size` units, `include_subfolders`, `junk`, and `recipients` are left entirely undocumented in both places.

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 opens with a clear verb+resource ('Search the user's mail') and then distinguishes the two search modes: index-backed `full_text` vs per-folder substring `subject`/`author`/`body`. It does not explicitly contrast itself with siblings `mail_list`/`search_global`, so the agent must infer the boundary, but the search semantics themselves are unambiguous.

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?

Gives concrete usage context: combine `full_text` with filters, use `cursor=nextCursor` to page, and route to `mail_get` when a body is needed. No explicit 'when not to use this / use X instead' against the many sibling search tools (search_global, mail_list, search_conversation), which keeps it short of a 5.

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