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

Annotations already cover the safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=true). The description adds genuinely non-structured context: guests are not notified, the call runs without asking first, and a Cotlet API key with app access is required. This exceeds the annotation baseline.

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?

Purpose is front-loaded in the first sentence and the four sentences each carry a distinct point (scope, behavior, undo, auth). "so it runs without asking first" is slightly awkward phrasing but not wasteful enough to drop the score to 3.

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 3-parameter mutation tool with no output schema, the description covers auth, notification side-effects, and the undo path. The only real gap is that it does not say how the check-in interacts with RSVP status or what a partial failure on a guest list looks like.

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 description coverage is 100%, so event_id, guest_ids, and undo are already documented with their source tools and default. The description reiterates undo's semantics ("set undo to true to remove a check-in") but adds nothing beyond the schema, so the 3 baseline applies.

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 and resource ("Mark guests as checked in at the door, or undo it") and clarifies the operation mirrors manual check-in from the guest list. It is clear on its own, but does not distinguish itself from adjacent siblings such as partiful_approve_guests or partiful_invite_guests, so the agent must infer the boundary.

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?

"At the door" and the undo instruction imply the check-in/undo workflow, and "like checking them in manually from the guest list" gives a useful mental model. However, there is no explicit when-not or statement of how this differs from approval or invitation tools.

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