school_mail_search

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

Annotations already cover the safety profile (readOnly, idempotent, openWorld, non-destructive), and the description adds real behavior beyond them: results are sorted by UID descending, and since is inclusive while before is exclusive. It says nothing about pagination behavior or result size caps, which keeps it short of a 5.

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?

A single dense sentence-block that leads with what the tool does and what it returns, then packs ordering, numeric bounds, date semantics and filters with no filler. Every clause maps to a parameter or a return behavior.

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 an output schema present, the description correctly need not detail return values, and annotations already carry the safety profile. What remains missing for a 9-parameter search tool is offset/pagination and mailbox-scope semantics, which are absent from both the description and the schema.

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 carries the full burden and does compensate for most of it: limit range 1–50, YYYY-MM-DD date format, since-inclusive/before-exclusive semantics, and the mapping of unread/sender/subject/text filters to parameters. offset and mailbox are left unexplained, so it is substantive but not complete.

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+resource ('搜索邮件') plus what it returns ('摘要和 UID'), which separates it from siblings like school_mail_read or school_mail_status. It does not, however, explicitly name the sibling that handles full-message retrieval, so the differentiation is inferable rather than stated.

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?

The list of available filters (unread, sender, subject, full text) implies when to reach for this tool, but there is no explicit 'use this instead of X' routing or stated prerequisite. Usage must be inferred from the filter surface rather than read directly.

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