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

Annotations already mark this write as destructive, non-idempotent, and open-world. The description goes well beyond that, disclosing non-obvious behavior: it requires login + organizer role, bypasses the cross-event 7-day dedup, still honors closed-invitation and decline backoff, and demands a re-read of SENT status afterward. These are exactly the operational traits an agent cannot infer from 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?

Dense but front-loaded: the requirement tag 【需要登录·主办方】 and the confirm-then-send instruction lead, followed by id sourcing, dedup/backoff constraints, and verification. Every clause carries operational weight, though the semicolon-packed style reduces readability 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?

With no output schema, the description covers auth/role prerequisites, side effects, dedup exemption, backoff behavior, the alternative path for multiple guests, and post-call verification (re-read SENT). An agent has enough to invoke it correctly; only the exact DM payload/return shape is left implicit.

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 50% (activityRef documented, invitationId undocumented). The description compensates by stating 'id取get_activity_invites', i.e. that the invitation id is sourced from get_activity_invites, which adds real meaning beyond the bare schema for the undocumented parameter.

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 (发...私信 / send a DM) and a specific resource (一位 SPEAKER 候选 / one SPEAKER candidate), with role scope (主办方) made explicit. It is distinguishable from batch/plan-based siblings, though the purpose statement is woven together with usage rules rather than stated cleanly up front.

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 explicit when-to-use (single immediate invite) and clear when-not guidance: '勿批量循环；多位用计划按间隔发' — for multiple recipients use the interval-based plan instead. This routes the agent away from looping this tool and toward the sibling set_guest_invite_plan, though the sibling is named only descriptively, not by tool id.

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