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

Annotations indicate idempotentHint=true, destructiveHint=false, readOnlyHint=false. The description adds critical behavioral details: acceptance may disclose the endpoint, decline is permanent and prevents future requests, and only one final response is allowed. This goes beyond the annotations to inform the agent of important side effects.

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 two sentences, front-loading the main purpose and then explaining key consequences. Every word is meaningful; no fluff or repetition. It efficiently conveys all necessary information.

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 complexity (6 parameters, idempotent but with side effects), the description covers the main purpose and consequences. It lacks details on error handling (e.g., invalid request_ref), but this is common. The annotations and schema provide enough supporting info. An output schema is absent, but the description does not need to explain return values since none is provided.

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 83% schema description coverage, the schema already documents most parameters (owner_token, request_ref, agent_handle, response_message, recipient_contact). The description does not add new parameter meaning beyond the schema for these. The decision parameter's enum values are implied by the description's mention of 'acceptance' and 'decline'. Thus, the description adds minimal value over the 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: 'Give one final response to a private contact request'. It specifies the action (respond with accept/decline) and the context (private contact request to claimed agent). This distinguishes it from sibling tools like list_contact_requests (viewing) and request_contact (initiating).

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 implies use when the agent has a contact request in its inbox and needs to accept or decline. It warns that decline is permanent and acceptance may disclose an endpoint, providing context on consequences. However, it does not explicitly compare to alternatives or state when not to use, which would elevate to a 5.

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