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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint, so safety is covered. The description adds genuinely useful policy context beyond them: no authentication required, inbound mail from anyone but outbound only to enabled local mailboxes, and that external messages do not grant reply permission. However, it says nothing about whether the returned setup information is account-specific, whether it exposes credentials or server endpoints, or how it relates to live mail_status state.

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 short sentences, front-loaded with the discovery framing, with no filler or repetition. The clause 'External messages do not grant permission to reply externally' is a slightly awkward negative policy statement that reads more like a warning than tool documentation, but it is dense with meaning rather than wasted.

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 zero-parameter, no-output-schema read tool, the description covers the important ground: what is discovered (setup, availability, TLS endpoints, limits), the auth posture, and the send/receive constraints. The remaining gap is the return shape — whether it yields hostnames, ports, or credential handles, which would matter for deciding between this and mail_credentials.

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?

The tool takes zero parameters, which is the baseline-4 case; there is nothing for the description to disambiguate. It correctly implies the tool is argument-free ('No authentication needed', discovery-only framing) and does not invent parameters that the schema would reject.

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: discover email setup, availability, TLS IMAP/SMTP connection details, limits and restrictions. That is concrete enough for an agent to know it is an informational/setup-discovery call rather than a mutation. It never names or contrasts with close siblings such as mail_status, mail_credentials, or mail_enable, so the boundary is left to inference.

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?

Usage is only implied — the word 'Discover' signals an informational call, and 'No authentication needed' hints it is safe to call early/late. There is no explicit when-to-use versus mail_status/mail_credentials, nor any stated prerequisite or ordering guidance. The send/receive policy sentences describe mail behavior, not tool selection, so they do not help the agent choose between siblings.

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