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

Adds substantial context beyond the annotations: the required auth scope, the fact that the first call mutates nothing, that argument validation mimics the real change and rejects unknown fields by name, and that the first call returns a summary plus confirm_token. This is exactly the mutation-safety 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?

Four short sentences, front-loaded with the action and permission, then the two-phase behavior. The parenthetical about unknown fields is slightly dense but carries genuine information; nothing is redundant.

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 still tells the agent what the first call returns (summary + confirm_token). It omits what the second call returns on success and what happens if the proposal/document state changed between calls, which is the main remaining gap for a destructive tool.

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 33%, and `confirm_token` is already documented in the schema. The description clarifies the confirm_token's role in the two-call flow and that arguments are repeated verbatim, but it never explains what `proposal_id` identifies or how it relates to `document_id`, leaving a real gap at low coverage.

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 ("Remove a document") and immediately scopes the required permission (`bookings:write`). It does not explicitly contrast with siblings like `edit_document`, but the destructive framing plus the two-call protocol makes its role unambiguous.

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 procedural guidance: call once to preview, show the summary to the person, then call again only after they agree, with the same arguments plus the confirm_token. It does not name alternatives (e.g., edit_document for non-destructive changes) or say when removal is inappropriate, which keeps it from a 5.

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