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

Goes well beyond the annotations: it discloses the login requirement, that results are ordered newest-first, that only the last 30 days are retained, and crucially that 'seen' means agent-viewed rather than the App's read receipt. This also explains why readOnlyHint=false on a listing tool — markSeen mutates state — so there is no contradiction with 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 login requirement and scope, then uses bracketed sections (组合链, 口径/坑) to group routing and caveats. Dense but each line carries information; slightly verbose, though nothing is redundant.

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 compensates by describing the return shape (data carries activityId, organizationId, inviteId for navigation) and the ordering/retention windows. Combined with the follow-up chain, an agent has everything needed to call it correctly.

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 100%, so the baseline is 3, but the description adds real meaning beyond the schema by explaining the interaction of unseenOnly and markSeen (marking this batch seen means it will not reappear under unseenOnly next time). That interplay is not derivable from the individual parameter descriptions.

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 (推送收件箱 = notification inbox) and immediately scopes what it contains (撮合/邀请/报名/组织通知) while excluding private messages via the named sibling list_my_conversations. An agent can distinguish it from list_my_invitations, list_my_organization_invites, etc. without opening any schema.

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?

Provides an explicit follow-up routing rule based on data.type, naming the four downstream tools (list_my_invitations, list_my_organization_invites, list_my_cooperation_requests, list_my_organization_notifications). It also disambiguates against list_my_conversations for private messages, leaving no inference required.

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