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

Beyond the annotations (destructive/non-idempotent/open-world), the description adds real behavioral context: the action is irreversible ('不可撤'), the organizer is notified as a side effect, and contactMode=SHARE discloses a contact snapshot that requires explicit consent with IN_APP as the default. This is substantive disclosure that the annotations alone do not convey.

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 dense but tight paragraph with the most important constraint (login required, irreversible decision) front-loaded, followed by the disclosure rule and the id source. Every clause carries information, though the run-on packing of five separate facts hurts scanability slightly.

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 5-parameter destructive mutation with 0% schema coverage and no output schema, the description covers login, irreversibility, notification, contact disclosure, the contactMode default, id sourcing, and the guest-profile follow-up. The main omission is the undocumented 'note' parameter and the reason enum semantics, which an agent might need.

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 description coverage is 0%, so the description carries the burden, and it partially does: it explains contactMode=SHARE vs the IN_APP default and the accept/decline decision plus reason. However it never mentions the 'note' parameter, does not enumerate the reason enum values, and gives no meaning for invitationId beyond its source. Adequate but with clear gaps.

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 verb+resource (respond to / accept-decline an activity invitation) and makes clear the acting party is '本人' with an explicit accept/decline decision. It does not explicitly distinguish itself from the several other respond_* siblings (respond_connection_request, respond_collaboration_invite, etc.), but the activity-invitation scope is unambiguous.

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 concrete usage context: login is required, the decision and reason must be confirmed first, and the id must be sourced from list_my_invitations. It also states a conditional follow-up (if profileNeeded=true, then update_my_guest_profile). It stops short of naming when NOT to use it or naming alternative respond_* tools, but the preconditions and sourcing are clear.

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