search_emails

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

With no annotations supplied, the description carries the full burden and does a good job: it discloses the no-body/token-saving behavior, the exact output line format, sort order (newest first), and a performance caveat that text search is slower. It omits read-only confirmation and any rate/volume limits tied to the limit parameter, 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?

The description is front-loaded with purpose and return shape before parameter notes, and every clause carries information without padding. The telegraphic style is dense but readable; a little more structure around the parameter notes would improve scanning.

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 an 8-parameter tool with 0% schema coverage and no annotations, the description should cover more of the surface area; limit, folder, account, and unread_only are silent gaps that can cause wrong calls (e.g. searching only INBOX by default). The presence of an output schema means return values need not be spelled out, yet it helpfully does so anyway.

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 8 parameters, so the description must compensate. It explains field values (subject/from/to/text), the since/before 'YYYY-MM-DD' format, and empty-query behavior, but leaves limit, folder, account, and unread_only 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 gives a specific verb plus resource (搜索邮件) and immediately fixes the scope: compact metadata only, no body, token-saving. It also states the exact record shape returned (id | date | sender | subject [flags]), which makes it clearly distinct from get_email, the sibling that returns full content.

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 establishes concrete usage contexts: field=text for full-text including body but slower, and empty query with no dates to list everything newest-first. It also implies the follow-up path by saying returned ids are passed to get_email/mark_email/move_email/delete_email/send_email. It doesn't explicitly say when to prefer get_email over this tool, so it falls short of full when/when-not coverage.

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