can_redo

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

Annotations cover the safety profile (readOnly, idempotent, non-destructive, closed-world). The description adds real behavioral context beyond that: what can_redo:false means after an undo, and exactly what the label field contains. It does not describe caching or failure modes, but the added semantics are substantive.

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 plus a return block. The scoping/routing guidance is front-loaded before the returns, and every sentence 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?

For a zero-param read-only predicate with annotations covering safety, the description is complete: it says what it reports, how to interpret a negative, when a sibling is better, and what the return shape means. Nothing an agent needs to call it correctly is missing.

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?

Zero parameters, so the baseline is 4. There is nothing to document and the description correctly introduces no parameter discussion.

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 check ('cheap yes/no on whether anything can be re-applied') plus the resource it exposes ('the LABEL of the entry redo would restore'). An agent can distinguish this from get_undo_state and the actual redo tool without opening the 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?

Explicitly routes to a sibling: 'Prefer get_undo_state for the whole picture in one call,' and explains the meaning of a false result. It does not explicitly say when this is the right choice versus redo itself, so it falls just short of a full when/when-not statement.

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