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

Annotations already declare this as a mutating, idempotent, non-destructive operation. The description adds the key behavioral fact beyond them: the change reverts to the program's target for that week, so the agent understands the resulting state. It doesn't warn that indices may shift after a revert or that the action is itself undoable.

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 trigger condition, then the input source, then the outcome, then the exclusion. No filler and nothing repeated from structured fields.

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?

Given an output schema exists and annotations cover the safety/idempotency profile, the description is nearly sufficient for a 3-parameter mutation. The remaining gap is the meaning of `week`, which the agent must guess.

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 only 33%, and only `idempotencyKey` is documented in the schema. The description compensates for `index` by tying it to get_weekly_review, but leaves `week` (integer 1-26) entirely unexplained - presumably the target week, but the agent must infer it.

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?

The description states a specific action on a specific resource: reverting one of the changes the Sunday review made to next week's plan. It distinguishes itself from the generic 'undo' sibling by naming it, though the '(verb)' is phrased colloquially rather than as a crisp 'Undo X' statement.

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 states when to use (the person doesn't want a Sunday-review change), when not to use (a change they made themselves - use `undo` instead), and where to get the required index (get_weekly_review). This is exactly the routing information an agent needs among 27 siblings.

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