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

Annotations already declare readOnly/idempotent/non-destructive/openWorld, so the safety profile is covered. The description adds meaningful context beyond them: the Bearer agent-key credential requirement, the fact that this server cannot provision an inbox, and a security warning that sender and subject are untrusted data.

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?

Three compact sentences, front-loaded with what the tool does, then credentials, then the safety caveat. No filler, though 'up to ten' is imprecise phrasing for a limit whose schema maximum is 10.

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 read-only, annotation-rich list tool with no output schema, the auth and untrusted-data notes are the most important additions and they are present. Still, with 0% schema coverage the description leaves pagination and filtering behavior undocumented, which is a real gap for a 3-parameter tool.

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%, so the description carries the full burden, yet it only hints at the limit cap ('up to ten messages') and says nothing about offset pagination or the unreadOnly filter. Two of three parameters — including the one the caller is most likely to need — are left entirely to inference.

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 messages in the authenticated mailbox'), which immediately distinguishes it from voidmail_read_email and the send-related siblings. It does not, however, explicitly name the alternative for reading a single message, so sibling differentiation is implied 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 description gives the precondition ('Requires an existing inbox's agent key... this server cannot create an inbox'), which tells the agent when the tool is usable. It stops short of routing guidance, e.g. pointing to voidmail_read_email for full message bodies or voidmail_setup when no inbox exists.

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