Remember or go back

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

Annotations already flag destructiveHint, and the description adds meaningful context: reverting keeps every ID, checkpoints persist with the project and survive saving, and the 'checkpoints' tool can list them. It does not fully specify all side effects of reverting, such as what happens to later checkpoints, but it goes beyond the structured annotation data.

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?

The description is three dense sentences with no filler. The purpose is front-loaded, the action semantics follow, and the persistence/listing detail is useful rather than redundant. Every sentence earns its place.

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 two-parameter tool with 100% schema coverage and an output schema, the description covers purpose, actions, persistence, and the key ID-preserving benefit. The main gap is that 'undoes back down to it' is somewhat vague about exactly what gets discarded on revert, but the destructiveHint annotation partially covers that.

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 description coverage is 100%, and the schema already documents both parameters including the default/revert behavior of 'action'. The description confirms that {label} is required by both actions and shows usage syntax, but it adds little semantic value beyond the input 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?

The description clearly identifies the resource (the current plan state) and the two operations: remembering a point via 'checkpoint' and undoing back to it via 'revert'. It is unambiguous about what the tool does, though it does not explicitly differentiate it from sibling undo/redo tools.

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 that 'checkpoint' is the default action and explains when to use 'revert', and it contrasts checkpointing with duplicating a version to justify why checkpointing preserves IDs. It lacks explicit guidance on when not to use this tool versus undo/redo, but the action-level guidance is clear.

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