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

Beyond annotations (idempotentHint=true), the description details idempotency_key reuse, required scopes, agent-scoped bearer key, and explicit limitations (cannot self-approve, dispatch postage, charge, destroy, or complete work). It also clarifies that the open_and_scan sample is test training, not paid OCR, providing real behavioral context that annotations do not cover.

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 a single dense paragraph without bullet points or section breaks, making it harder to scan. However, every sentence carries necessary information given the tool's complexity and deprecation status, so it is not verbose. A more structured layout would improve readability, but the content is appropriately sized.

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?

Given the tool's complexity (three action types, nested request object, auth requirements) and the presence of an output schema, the description covers all essential context: deprecation and alternative, prerequisites (read capabilities first), per-action constraints, idempotency guidance, authentication scopes, and limitations. Nothing critical is missing for an agent to invoke it correctly.

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?

With 0% schema description coverage, the description compensates by explaining key parameter constraints: confirmed and destructive_confirmed should be false, forward requires a complete US destination and mail class, discard needs subsequent confirmation, and idempotency_key must be reused with identical body and expected_version. While not exhaustively covering every field, it adds significant meaning beyond the raw schema.

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 clearly states the tool's purpose: proposing handling actions (open_and_scan, forward_original, discard_original) for agent inbox items via a specific endpoint. It explicitly distinguishes itself from the replacement tool request_inbound_action, and lists what it cannot do, leaving no ambiguity about its scope.

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 begins with the explicit deprecation and points to request_inbound_action as the preferred alternative. It provides concrete usage conditions: require confirmed:false and destructive_confirmed:false, read capabilities/version first, forward needs US destination and mail class, discard needs subsequent confirmation, and never substitute another key or mail API after denial. This is comprehensive guidance for when and how to use the tool.

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