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

Annotations only supply destructiveHint=false, so the description carries the burden and does so well: it discloses that the proposal is set to CONVERTED in the same transaction and linked to the activity, that invitees are re-fetched from the currently visible proposal and must not be injected, that cloud users are invited only after publishing, and that no notification is sent unless notifyInvitees=true. It also describes idempotent behavior (already-converted proposals return the original activity rather than rebuilding) and the preview-hash invalidation rule.

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 preview/confirm contract is front-loaded and every clause carries information, but the semicolon-chained style and dense noun stacking make it harder to parse than it needs to be. No sentence is wasted; readability is the only cost.

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 10-parameter mutation with nested activity/signup objects and no output schema, the description covers lifecycle, side effects, notification defaults, idempotency, and key constraints. It does not state what the response returns (e.g., the created activity and previewHash) or permission requirements beyond the login hint, which leaves a small but real gap.

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 40% schema description coverage, the description has to compensate and largely does: it explains preview and previewHash semantics, the exclusion list, notifyInvitees defaulting to no notification, guestUserIds for cloud users post-publish, and the constraint that signup is platform-hosted only and activity follows the formal schema. Gaps remain for appActivation, organizationId/proposalId sourcing, and the large nested activity object's optional fields.

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 names a specific action and resource: publishing an organization proposal activity via a preview/confirm flow, with an explicit note that a generic activity draft must not be substituted ('禁通用草稿替代'). It therefore separates itself from publish_activity_draft and create_organizer_activity, though those siblings are not named directly, forcing some inference.

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 a clear workflow: call with preview=true to see the full text/time/location/closed audience/invitee list, then resend the same activity/signup/excludeUserIds plus previewHash with preview=false to publish, and re-confirm if the preview changed. It also states offline activities require a location and that already-converted proposals return the original activity. What is missing is explicit routing guidance naming which alternative tool to use when this one does not apply.

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