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

Beyond readOnlyHint=true, it discloses that self is excluded from results, that channel availability is server-decided and empty means the invite path is blocked, that ended activities are read-only for progress, what extra fields come back (smsRetryAt, hasInviteLink), and a privacy guarantee that no contact details, links, or tokens are returned. That is substantial behavior disclosed nowhere in the annotations.

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-loads the access mode (login/read-only) and then packs scope, defaults, constraints, and return notes into tight clauses with no filler. The telegraphic semicolon-chained style is efficient but dense enough that a reader must parse carefully.

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?

With no output schema, the description still names the notable returned fields and the privacy boundary, and it covers the edge cases (missing activityId, no App channel, empty channels, ended activity) that govern whether the call yields anything useful. Nothing an agent needs to call it correctly is missing.

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%, with activityId carrying no schema description; the description fills exactly that gap by explaining it defaults to the already-associated activity. It adds real meaning for the one undocumented parameter rather than restating organizationId/proposalId, which the schema already covers.

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 read operation (viewing a proposal's currently visible meetup invitees, channels, and acceptance progress) and immediately marks scope with '不含本人'. This cleanly separates it from invite-side siblings such as invite_organization_meetup_to_activity and from people-listing siblings like list_organization_activity_people.

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?

Gives concrete conditions: activityId defaults to the already-linked activity, cloud users have no App channel, channels are service-determined and an empty value means invitation is impossible, and a concluded activity is progress-view only. It also routes dedicated-link needs to the invite tool with MANUAL selection, though that alternative is only mentioned for one narrow case rather than as a general 'to invite use X' rule.

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