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

Annotations declare idempotentHint=false, but the description explicitly says '重复响应幂等' (repeated response is idempotent). This directly contradicts the structured annotation. Although the description adds useful context about login and contact disclosure, the contradiction must be scored as a serious transparency failure.

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 and front-loads the login requirement before behavior and chain details. Every sentence carries information, though the bracketed style is dense and slightly less readable.

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 privacy-sensitive mutation with no output schema, the description covers login, confirmation, rejection re-send behavior, and the recommended chain. However, the incorrect idempotency claim undermines completeness and could mislead an agent about repeated calls.

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 100%, so the baseline is 3. The description adds a prerequisite for accept=true (explicit confirmation and at least one contact method), but it does not add syntax or format details for exchangeId or conversationId beyond what the schema already provides.

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 states a specific verb+resource: replying to a pending contact-exchange request in a 1-1 DM. It names accept/reject behavior and the prerequisite chain get_contact_exchange_state→respond, but it does not explicitly distinguish this tool from sibling request_contact_exchange.

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?

It gives clear context for use: login is required, accept=true requires explicit confirmation and at least one contact method, and reject allows a later re-send. The combination chain also tells the agent to check state first, though no explicit when-not guidance is provided.

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