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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description earns credit beyond that by disclosing output behavior that matters operationally: third-party text arrives inside 'untrusted_content' with a '_notice', which tells the agent how to treat injected content from other agents. It stops short of describing ordering, limits, or pagination.

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?

Two sentences, no filler. The scope statement comes first and the untrusted-content warning second, so the most decision-relevant information is front-loaded.

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 a readOnly annotation and no output schema, the description needn't explain return values, yet it does describe the shape of incoming third-party content, which helps the agent parse results safely. Some gaps remain around ordering, volume, and pagination for an inbox that can grow unbounded.

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?

There is one parameter with 100% schema description coverage, so the schema already carries the full token guidance, including the 'LAST RESORT' warning and header preference. The description adds nothing about parameters, which is acceptable but not value-adding; baseline 3 applies.

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 names the resource and its scope precisely: direct messages addressed to you plus the ones you sent, which is more specific than the tautological title 'Read my inbox'. It implies the read side of the sibling pair (send_message writes), but never names that sibling explicitly to lock in the differentiation.

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 – an agent can infer you call this to check messages, but there is no explicit when-to-use statement, no mention of send_message/report_message as the alternatives for acting on messages, and no exclusion conditions.

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