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

With only destructiveHint=false supplied, the description carries the burden and delivers: it explains the preview/confirm safety flow, that MANUAL merely prepares a personal link and does not send, that resends are subject to cooldown/accept/reject restrictions, and that phone numbers are never exposed. It also decodes PREPARED/PENDING/ACCEPTED so the agent will not misreport delivery or attendance.

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?

Dense but well ordered: purpose, then preview/confirm mechanics, then per-parameter rules, then status caveats and privacy. Every clause carries information, though the telegraphic style and unexplained opening fragment cost some readability.

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 mutation tool with minimal annotations and no output schema, this covers the safety flow, side effects, per-channel behavior, status interpretation and privacy constraints an agent needs before sending real invitations. Remaining gaps (preview response shape, recipient-count limit) are minor.

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 only 25%, so the description must compensate, and it does for preview (default true, preview mode), previewHash (required on the confirm call), channel (taken from the latest invitationActions.channels; MANUAL does not send) and resend (explicit user request only). It adds nothing about userId semantics or the 60-recipient cap that the schema enforces.

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 second clause states the action precisely: continue inviting members who already exist in the invitation ledger, which separates it from guest-creation tools like add_activity_guest. The leading fragment "登录/对外邀请" is cryptic and the description never names a sibling tool it should be preferred over, so it stops short of a 5.

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 two-step protocol: call with preview=true (the default) to see roster, channel and resend state, then repeat the same parameters plus previewHash with preview=false. It also gates resend=true behind an explicit user request. It does not route the agent to alternatives (add_activity_guest, send_guest_invite_now, invite_activity_cloud_member_manually) for non-ledger recipients.

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