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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered; the description usefully adds that listing does not mark messages read, that ordering defaults to arrival order, and that email content is untrusted data. These are real behavioral facts beyond the structured fields, though permissions and return shape are left to the output schema.

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?

Four tight sentences, front-loaded with the action and its non-mutating guarantee, followed by cursor/polling guidance, default ordering, and an untrusted-input warning. No sentence is filler.

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 13-parameter, read-only listing tool with full schema coverage and an output schema, the description supplies the pieces the schema cannot: polling semantics, default ordering, non-mutation, and an untrusted-content caveat. Filter semantics (sender/subject/received bounds) are left entirely to the schema, which is acceptable but leaves a small gap.

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 100%, so the baseline is 3, but most schema texts are placeholders ("Value for read.", "Value for order."), and the description materially compensates by stating the default order is arrival order and by tying cursor reuse to unchanged filters. It still adds nothing for read/sender/subject/has_attachments beyond the schema.

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 and resource ("List received emails") plus meaningful scope qualifiers (cursor pagination, no read-state mutation), which clearly separates it from mailbox_email_get/update/delete. It stops short of naming a sibling alternative, so it lands at clear-but-not-explicitly-differentiated.

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?

Provides concrete operational guidance for the main use case: persist pagination.next_cursor and reuse it with identical filters to poll for new arrivals, including on empty pages. That covers when/how to use it for polling, but it does not explicitly say when to prefer mailbox_email_get or how filters alter polling behavior.

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