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

Annotations already flag destructive=true/idempotent=false/openWorld=true, but the description adds substantial context beyond them: autoStart auto-DMs strangers and requires reading target/pace/count back to the user, editing brief only invalidates the running generation and pauses SPEAKER, old candidates are neither deleted nor auto-re-found, and new candidates are appended. This is exactly the side-effect detail annotations cannot 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?

Front-loaded with the login/organizer requirement and the config summary, and every sentence carries distinct information. It is a dense run-on paragraph, however, so navigation is slightly harder than an ideally structured definition.

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 destructive, open-world mutation with 8 params, low schema coverage and no output schema, the description supplies prerequisites, the multi-step workflow, confirmation requirements, and side effects. An agent has what it needs to call it correctly and safely.

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 13% (just activityRef), so the description must carry the load, and it does conceptually map all 8 params: role, targetCount/backupCount (数量/备选), intervalMinutes (节奏), inviteTtlHours (过期), brief (≤600 chars, omitting costs an extra LLM call), autoStart (ATTENDEE-only). The mapping is implicit in Chinese rather than per-parameter, so precise semantics are slightly under-specified, preventing a 5.

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: configuring the guest/audience invite plan, enumerating what is configurable (count/backup/pace/expiry/selection brief). It clearly distinguishes itself from neighboring tools (update_guest_candidates, set_guest_invite_plan_status, add_guest_candidates) by naming them in the workflow.

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?

Explicitly lays out when/how to use it: initial SPEAKER setup goes get_activity_invites → update_guest_candidates → set_guest_invite_plan_status(start); autoStart is reserved for ATTENDEE while SPEAKER must be manually started. It names alternatives and conditions that select them with no inference required.

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