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

Annotations already mark it readOnly/idempotent/non-destructive. The description adds beyond that: it requires login (【需要登录】), and it notes that ACCEPTED is a snapshot from that moment, which implies the data may be stale. This is useful extra behavioral context.

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?

It is a compact, front-loaded format: first the login requirement and what is read, then the state-to-action chain. Every clause is doing work.

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 single-parameter read tool with no output schema, the definition is complete. It covers auth, what is returned (myContacts/canRequest), and the branch conditions. The only small gap is that the exact field names and the format of the response are not listed.

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 coverage is 100%, and the single conversationId parameter is fully documented, including the 'only 1-1 conversations' constraint. The description doesn't need to repeat it, so the baseline 4 for zero effective parameters applies here.

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 that it reads the human-DM contact exchange state, plus myContacts/canRequest. The verb '读' and the resource '交换状态' are specific, and it is distinguishable from the sibling tools that perform mutations in this chain.

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 an explicit combination chain: when state is '可请求' go to request_contact_exchange, when 'peerPending' go to respond_contact_exchange, and when '本人无联系' go to add_profile_link. This details exactly when to use which alternative.

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