search_mail

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

With no annotations, the description carries the full behavioral burden and does disclose meaningful traits: the type-safe ref distinction (drafts are not disguised as replyable messages), server-side name/pinyin disambiguation, and the resume_token handoff to continue_action. It omits safety profile (read-only vs mutating), pagination behavior despite limit/offset, and rate limits, so it is strong but not complete.

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?

Dense but front-loaded: purpose and return contract come first, then default behavior, then the resume flow. Four short sentences, each carrying information with no filler. Slightly terse for the amount of undocumented surface it must cover.

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?

An output schema exists, so return values need not be explained, and the description does describe the ref/resume contract. But against 11 parameters at 0% schema coverage and zero annotations, the description leaves most filter parameters semantically undefined, which is a real gap for a query tool of this complexity.

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 11 parameters, so the description must compensate and largely fails to. It only alludes to filter semantics indirectly ('无过滤条件时' covers folders defaults, and '姓名拼音或完整邮箱由 Server 解析' touches sender/participant query resolution), leaving after, before, limit, offset, lookback_days, unread_only, has_attachments and subject_contains completely undocumented in both schema and description.

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 ('统一查找邮件') and immediately specifies the return contract: message_ref for regular mail, draft_ref for drafts. This distinguishes it from read_mail (single message retrieval) implicitly, though it never names a sibling as an alternative. Purpose is clear but sibling differentiation is only partial.

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 one concrete usage scenario (no filters → lists recent inbox/sentitems mail) and explains that a resume_token is returned when user disambiguation is needed, which continue_action restores. However, it never states when to prefer search_mail over read_mail, nor any conditions/exclusions around filtering. Guidance is implied and incomplete.

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