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

Annotations only say non-readonly, non-open-world, non-destructive; the description goes well beyond by disclosing the 10-minute undo window, that deleted classes are restored, and the atomic refusal rule if any class changed since. These are exactly the constraints an agent needs before invoking a corrective mutation, and nothing contradicts destructiveHint=false since the operation restores prior state.

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 short sentences, zero filler, and the scope/behavior details are front-loaded before the refusal caveat. Every clause carries information an agent must have.

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 one-parameter corrective tool with no output schema, the description covers purpose, time limit, and refusal semantics. It does not say what the agent receives on refusal (error shape, partial application) or whether authorization differs from edit_classes, which is a minor remaining gap.

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 100% and the schema itself explains the single parameter ("The undo id edit_classes returned"), so the baseline is 3. The description reinforces the edit_classes origin but adds no format, syntax, or sourcing detail beyond the schema.

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?

"Put every class an edit_classes change touched back exactly as it was, deleted ones included" names a specific verb (restore/undo), a specific resource (classes touched by an edit_classes change), and explicitly ties itself to the sibling tool it reverses. An agent can distinguish this from edit_classes, save_class, or remove_class without opening any schema.

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 states the trigger (an edit_classes change you want reverted), the hard precondition (within 10 minutes of it), and the blocking condition (refused when any of the touched classes was changed since). That is when-to-use plus when-not-to-use in a single sentence.

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