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

Goes well beyond the lone destructiveHint=false annotation: discloses that login is required, that the recipient is notified but notification does not imply acceptance, that execution re-validates mutual visibility, blocking, status and quota, and that auto-filling the contact from the login phone/profile is forbidden. These are exactly the side-effect and failure-mode facts an agent needs before committing a write.

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?

Very dense with almost no filler, but it is a single semicolon-chained paragraph that front-loads the login tag rather than the action, and interleaves scoping, consent flow, and contact rules without ordering. Information-to-token ratio is high; parseability is not.

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 9-parameter mutation with no output schema and thin schema descriptions, it covers the preview/execute contract, consent, contact-sharing constraints, recipient notification, and execution-time re-validation. Gaps remain around what the preview returns, duplicate-request behavior, and quota specifics, but nothing that would cause a wrong invocation on the happy path.

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 only 22% schema description coverage across 9 parameters, the description carries most of the semantic load and does so for the critical ones: preview/previewHash/consent form a described handshake, activityId/organizationId are explained as mutually exclusive scoping with an all-empty public default, and contact is tied to shareContactConsent. targetUserId and the previewHash provenance (presumably returned by the preview call) are left implicit, which keeps it short of a 5.

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 never states plainly that it sends a connection/communication request to a target user; the action is only inferable from the title and from side remarks like "会通知对方，不代表接受". It also opens with a login precondition rather than a purpose statement, so the agent must reconstruct the verb+resource from surrounding clues.

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?

Strong two-phase guidance: default is preview, and execution requires re-calling with identical params plus previewHash, consent=true, preview=false. It also states the activityId/organizationId mutual-exclusivity rule and that omitting both means public scope. It does not, however, contrast itself with close siblings such as create_quick_contact_request or respond_connection_request.

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