Build Recipe

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

With readOnlyHint=false and destructiveHint=false, the description adds the specifics: validation of recipe/inputs against the declared schema, a deterministic build, and the concrete sub-operations (geometry + publish_interface + declare_intent). It also lists the return payload, which partially compensates for the missing output schema. It does not contradict the annotations.

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 three sentences are tight; the first sentence states the action, the second explains validation/build order, and the return list is necessary because there is no output schema. The issue reference adds noise, so it is not flawless, but the definition is still efficiently organized.

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 no output schema, the description is reasonably complete: it names the required document context (active document), the validation behavior, the build steps, and the returned fields. It does not mention where recipe IDs come from or that an active document must already be open, but the wording 'into the active document' and 'registered' imply those prerequisites.

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?

Because schema description coverage is 0%, the description must carry param meaning, and it does: 'recipe' is a registered recipe and 'inputs' are the new parameters subject to typed units and ranges. It stops short of detailing the inputs object's key structure or how defaults work when inputs are null, but it gives enough semantic context for a caller.

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?

Opening verb 'Build' names the core action on a specific resource ('registered part recipe') and scopes it to the active document. The clarification about re-running with new parameters removes ambiguity between creating and regenerating, and the action distinguishes this from static siblings like recipe_list, recipe_schema, and recipe_validate.

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's context is clear—use this to create or regenerate a registered recipe's geometry in the active document—but it never explicitly names when to prefer recipe_validate or recipe_schema. It implies the distinction by saying it both validates at the door and then performs the build, but leaves the 'validate-only' path to inference.

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