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

Beyond the annotations (destructiveHint=true), the description discloses the conditional destructive behavior ('Set consume=true to delete what is returned') and adds the 50-payload limit, inbox expiry reset, and the security warning to treat all returned content as untrusted input. This rich context goes well beyond the structured annotations and clarifies the exact conditions under which the tool mutates 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?

The description is compact yet comprehensive, with no filler. It is front-loaded with the core purpose, followed by usage details, behavioral side-effects, a limit, and a security note. Each sentence earns its place, making it highly efficient for the information conveyed.

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 no output schema, the description covers the return payload structure ('Each payload has its method, headers, body and arrival time') and the pagination limit ('Returns at most 50 payloads per call'). It implies the presence of next_after by instructing to pass it from a previous poll, and it addresses side effects and security. For a 5-parameter tool with no output schema, this is a complete and self-sufficient explanation.

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 input schema has 100% coverage, so parameters like inbox_id, token, after, limit, and consume already have descriptions. The tool description adds extra meaning by explaining the relationship between after and next_after from a previous poll, and by clarifying that consume is optional and defaults to false. It also connects limit to the documented 50-payload cap, though it doesn't add much for the identity parameters.

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 begins with a specific verb and resource: 'Read requests delivered to an inbox since you last looked.' This clearly distinguishes the tool from siblings like inbox_create and inbox_delete, and the phrase 'since you last looked' adds a unique stateful poll behavior. It also mentions the optional consume mode, but the primary purpose is unambiguous.

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 provides concrete usage instructions: 'Pass after=<the next_after from your previous poll> to get only new ones; omit it to start from the beginning' and 'Set consume=true to delete what is returned.' It also explains the behavioral consequence of polling ('Polling also resets the inbox expiry'), which guides when to use the tool. However, it does not explicitly name alternative tools or scenarios where other tools would be preferred, so it's slightly below a perfect score.

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