Refreeze Recipe Revision

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

Annotations already establish readOnly=false, destructive=false, and idempotent=false. The description adds non-obvious behavior: a new revision is created, the old revision and its provenance are untouched, an auto-filled reason is generated, the return value should be launched, and two specific 409 error cases are disclosed. This goes well beyond the annotation signals.

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?

Three dense sentences with no filler. Each sentence earns its place: purpose and effect, non-destructive behavior with return guidance, and error conditions. The most important information is front-loaded.

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 purpose, exact effect, non-destructive behavior, return value, and failure modes, and the tool has an output schema plus only two simple parameters. It is nearly complete, but an explicit mapping of 'recipe_id' and 'number' to the operation would remove the last ambiguity.

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 0%, and the description never explicitly names 'recipe_id' or 'number'. It implies the recipe through 'same recipe' and the source revision through 'the revision' in the 409 clause, but parameter semantics are largely left to inference from property names.

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 opens with a concrete recovery scenario ('Recover from engine_changed'), then states the specific operation: creates a new revision of the same recipe with the same specification, frozen on the current engine. This clearly differentiates it from sibling revision/draft tools by emphasizing refreezing rather than editing or creating drafts.

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 first phrase 'Recover from engine_changed' gives an explicit condition for use, and 'without bypassing the safeguard' signals the intent. It does not name an alternative sibling or state an explicit when-not-to-use rule, though the 409 cases implicitly delimit invalid calls.

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