undo_preview

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

No annotations are provided, so the description carries the burden of behavioral disclosure. It clearly states this is a non-executing dry-run, shows what output will contain (diff, target inversion calls), and gives a read-cost estimate. It does not disclose the exact output format beyond the schema's response_format enum, but the key safety-relevant behavior (no execution) is explicit.

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 compact and front-loaded, with the core purpose stated in the opening phrase. The read-cost hint is a useful addition, and there is no redundant text or repetition of schema details.

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 non-executing preview tool with a fully-covered schema and no output schema, the description covers the essential context: what it does, what it doesn't do, and the cost. It could mention expected response format more explicitly, but the response_format parameter already documents the options. No critical gap for an agent to use it correctly.

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%, so parameters are already well-documented. The description adds meaning by tying mutation_id to a receipt id and mentions the optional check behavior but does not add much beyond the schema. Baseline 3 is appropriate since the schema does the heavy lifting.

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 this as a dry-run for undo_mutation, explicitly stating it shows what a receipt-driven revert would do (diff of before/after, target inversion calls) without executing. This distinguishes it from the actual mutation tool and other read tools, making its purpose unmistakable.

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 explicitly frames the tool as a preview before executing undo_mutation, naming the related mutation tool and stating that it does not execute. The '0-2 reads' cost hint additionally signals when it is safe to invoke, giving clear context for when to use it versus the actual undo operation.

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