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

Annotations only supply destructiveHint=false, yet the description discloses login requirement, the distinct effect of each channel (MANUAL grants activity visibility via a generated link), that the tool does not return phone numbers, that previewHash must be refreshed when the list or content changes, and that a failed send must not be retried on another channel. That is materially more than the annotation covers for an externally visible invitation action.

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?

Front-loaded with the login gate, then channel semantics, then the preview/confirm workflow. Dense but every clause carries operational information; the bracketed 【组合链】 shorthand is terse and slightly harder to parse than prose.

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 6-parameter mutation with no output schema, the description covers the prerequisite, the two-step preview confirmation flow, and failure handling. Minor gaps remain around returned preview fields and rate limits, but nothing critical to invoking correctly is absent.

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 67% and the schema leaves channel undescribed; the description supplies the semantics of APP/SMS/MANUAL and explains exactly how preview and previewHash are used together. It does not explain resend or the recipients list limits (max 6).

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?

States a specific verb+resource: 发站内邀请/发短信 for matching pairs (匹配对象) to an activity, and names the three delivery channels. It never explicitly disambiguates from near-siblings such as invite_organization_meetup_to_activity or send_activity_ledger_invitations, so the agent must rely on the tool name to pick this one.

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 【组合链】 segment gives an explicit procedure: obtain channels + invitable activities, call with preview to verify activity/list/channel, then get user confirmation, then re-call with the original params plus previewHash and preview=false. Missing is any statement of when this tool is the wrong choice versus the sibling invite tools.

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