Create explicit checkpoints

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

The description adds value beyond annotations by explaining that the checkpoint is 'committed', 'without modifying any project asset', and that restoring reproduces state 'byte for byte'. Annotations already indicate non-destructive, but the description provides deeper behavioral context.

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 sentences, no filler. Every clause adds meaning: the action, the scope, the side-effect-free nature, and the comparison to automatic checkpoints.

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?

The description covers the tool's purpose, safety profile, and use case adequately for a moderate-complexity tool. It does not explain the output schema or return values, but those are provided separately. Minor gap: no mention of label semantics.

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?

With 0% schema description coverage, the description should compensate but only vaguely implies that 'paths' refer to project files. The 'label' parameter is not addressed. The schema constraints (maxItems, etc.) are not reiterated or explained.

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 states it 'Creates committed recovery checkpoints of the exact current bytes of 1 to 32 project files' and emphasizes it is an explicit save point distinct from automatic checkpoints. The verb and resource are specific, and the scope (number of files, no modification) is precise.

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 positions the tool as 'an explicit save point before risky work', giving clear context for when to use it. However, it does not explicitly exclude any scenarios or mention alternatives among siblings like tiled_preview_checkpoint_restore.

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