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

Annotations only declare readOnly=false, destructive=false and openWorld=true, so the description carries real weight here: it discloses the concrete side effects (after-visit sign-up messages stop, the review ask is dropped) and a 10-minute reversal window via `undo: true`. That is exactly the kind of consequence an agent needs before mutating state; only auth/permission requirements and whether already-sent messages are affected are missing.

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?

Two tight sentences: the effect is front-loaded and the undo clause is appended as a distinct, immediately scannable caveat. No filler.

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 with no output schema, the description covers what changes and how to reverse it, which is the core need. It does not say what the call returns or what happens if the contact has no pending sign-up sequence, but the essential operational picture is present.

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 67%; `contact` and `brand` are documented in the schema, while `undo` has no schema description and is explained only here ('undo: true reverses it within 10 minutes'). That adds genuine meaning beyond structured fields, though the 10-minute window is not framed as a hard expiry guard.

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 ('Record that this contact has signed up'), which is unambiguous and unlike any sibling (no other tool marks sign-up state). It could have named what it is *not* — e.g. how it differs from `set_contact_name_and_note` or `close_request` — but the operation itself is clear.

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?

The description implies the trigger condition (a contact has signed up) and offers a reversal path, but it never says when to prefer this over neighbouring actions like `close_request`, nor when it should not be applied. Usage is inferred rather than stated.

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