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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, so safety is covered. The description adds real value beyond that: it defines the failure state ('unavailable: the site can no longer run its own undo') and names every returned field, which is the main thing an agent cannot infer from structured data here.

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?

One dense sentence with the status enumeration and the return-field list front-loaded and no filler. It is packed close to the limit but every clause (including the 'unavailable' gloss) carries information.

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 takes on the return-value burden and discharges it by listing expires_at, seconds_remaining, receipt_id, and the reverse-op provider/tool_name. What remains missing is the provenance of the undo token and how this relates to fleet__undo, which is a meaningful but bounded gap for a one-parameter read 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 0% and the single parameter is a bare string, so the description must carry the load. It names the token's role but never says where an agent obtains an undo token, whether it is opaque or formatted, or what happens with an invalid/unknown token.

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 ('Look up an undo token and report ... status') and enumerates the exact status vocabulary returned. It does not, however, distinguish itself from the closely-related siblings fleet__undo and fleet__restore_status, so an agent must infer the boundary itself.

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?

Usage is only implied: checking a token's status before acting is the obvious reading, but the description never says 'call this before fleet__undo' or 'do not call this to perform the undo.' No alternative or exclusion is named despite fleet__undo and fleet__restore_status sitting in the same namespace.

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