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

With readOnlyHint already covering safety, the description adds real behavioral context: permission requirements per scope, what data is deliberately absent (no phone numbers, answer sheets, notes, or tokens), and precise status semantics (PREPARED means merely prepared, PENDING means in flight not delivered, ACCEPTED is not the same as registered). It also describes the default view (all authorized history) and the response envelope keys (nextOffset, matchingCount, summary, nextCursor=null).

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?

Every clause carries distinct information — scope, permission model, sibling routing, status semantics, exclusions, pagination, response keys — with essentially no filler. The semicolon-delimited structure is dense but scannable, though the opening login note is the least valuable element and is not front-loaded by importance.

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?

There is no output schema, so the description compensates by naming the fields an agent will need (invitationActions, nextOffset, matchingCount, summary, nextCursor) and by explaining what the statuses do and do not mean. Combined with the permission and exclusion notes, an agent has enough to call it and interpret the result without further probing.

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 20%, so the description carries most of the weight, and it does: it documents userId/status as filters, offset/limit as pagination, the meaning of the status enum values, and how nextOffset is used to continue. activityRef semantics come from the schema itself, so the only residual gap is limit bounds, which the schema already constrains.

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 resource — the per-person invitation fact/channel history for one activity — and explicitly contrasts it with get_activity_invites (plans and candidates only). The telegraphic phrasing ('活动逐人邀请事实/渠道历史') and the leading '登录;' fragment make it slightly harder to parse than it needs to be, but an agent can still tell what this returns and how it differs from the sibling.

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?

Names the alternative (get_activity_invites) and when to prefer it, states the scope split (ALL requires management permission, MINE shows only one's own invitations with service-side clipping), and routes continuation of invitations to send_activity_ledger_invitations with the note that confirmation is required. It also redirects signup questions to the participation source rather than this ledger.

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