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

Annotations already declare readOnlyHint=true, non-destructive, and idempotent, so the safety profile is covered. The description adds valuable behavior beyond that: the available=true filter, the shared-alias limitation, and a security note that addresses are untrusted data—useful for guarding against prompt injection.

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 the core action, then layers constraints, downstream usage, and a safety note. Every sentence adds useful information, though the final security sentence is somewhat abrupt.

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 low-complexity, one-parameter read tool with rich annotations and no output schema, the description covers what is returned, applicable filters, downstream usage, and a security caveat. The only minor gap is not mentioning how to discover mailboxId, but a sibling list_mailboxes likely covers that.

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 sole parameter mailboxId has no schema description (0% coverage). The phrase 'for one connected mailbox' implies what mailboxId identifies, but the description does not explain format, how to obtain a valid id, or examples. With just one obvious parameter, this is adequate but under-specified.

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 states a specific verb ('List') and precisely names the resource: the primary address plus currently authorized sending aliases for one connected mailbox. It clearly distinguishes this lookup tool from sibling tools like prepare_draft and revise_draft by explaining its role in supplying senderIdentityId.

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 clear conditions: only identities with available=true can be used here, shared aliases require webmail, and exact returned ids feed into draft preparation/revising. It does not name an alternative MCP tool for shared aliases, but the usage context and exclusion are strong.

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