update_custom_recipe_steps

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It discloses that this is a partial update preserving other fields, and explains dry_run validation behavior. It does disclose the steps_json format requirements. However, it doesn't state auth requirements or error behavior on invalid JSON, though the format details are reasonably thorough.

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 sentences, each earning its place. The description is efficiently organized: core action first, then format details, then usage constraint, then validation behavior. Slightly dense in the second sentence but not wasteful.

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 tool has an output schema (which explains return value shape) and 3 parameters with 0% schema coverage. The description provides substantial detail on parameter semantics and usage constraints. Given the moderate complexity (annotations, dry_run mode), the description is fairly complete, though it could add more on error handling for malformed JSON.

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%, so the description must compensate for the schema's lack of parameter documentation. It explains steps_json format in detail (JSON array, plain text or STEP objects with TTS/MODE/INGREDIENT annotations) and dry_run semantics (validate without patching). It does not explain recipe_id, but that name is self-explanatory.

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?

Specific verb+resource: 'Replace a custom recipe's preparation steps.' Clearly states the action (replace steps) and the target (custom recipe). Distinguishes from sibling update_custom_recipe_ingredients and upload_custom_recipe tools by focusing specifically on preparation steps. The partial-update nature is stated.

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?

Provides explicit usage guidance: separate steps for weighing/adding vs cooking/mixing/chopping/kneading. States a constraint that a single step cannot contain both INGREDIENT and TTS/MODE annotations. Explains dry_run behavior for validation without patching. This is actionable guidance beyond implicit context.

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