Validate an entire native CAD plan before execution with dry run default, using a request ID to prevent repeat execution and preserving partial successes on failure.
Validate an entire native CAD plan before execution. Dry run defaults true. request_id prevents repeat execution in this process. Partial successes remain on failure; no plan rollback.
| Name | Required | Description | Default |
|---|---|---|---|
| steps | Yes | ||
| dry_run | No | ||
| request_id | Yes |
Changes observed during successful MCP inspections.
v0.7.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Goes meaningfully beyond the annotations by disclosing the default of dry_run, the de-duplication behavior of request_id, and critically that partial successes persist with no rollback on failure — the key behavioral risk for a destructiveHint=true tool. It still does not say what validation feedback looks like or how a validation failure is signalled.
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 short, front-loaded sentences with no filler; the validation purpose and the dry_run default lead. The terseness contributes to the execution-vs-validation ambiguity, but no sentence is wasted.
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 two highest-stakes facts (dry-run default, no rollback on partial failure) for a destructive plan-execution tool. Gaps remain around the steps payload contract and the nature of the validation result, which matter given no output schema, so it is strong but not complete.
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 carry the burden, and it only explains dry_run's default and request_id's purpose. The most important parameter, steps (a 1-32 item array of tool/arguments objects), is never described — no indication of what tool names are permitted, what arguments look like, or the 32-step ceiling.
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?
States a specific verb and resource ('Validate an entire native CAD plan'), which distinguishes it from the atomic modelling siblings like add_box or cut_profile. However, it frames the tool purely as validation while annotations (readOnlyHint=false, destructiveHint=true) and the steps array indicate it also executes a multi-step plan; the ambiguity with sibling pro_validate_design is not addressed.
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 phrase 'before execution' plus 'dry run defaults true' implies a pre-flight usage pattern, and the request_id note hints at retry semantics. But there is no explicit when-to-use/when-not guidance, no mention of pro_validate_design or pro_run_plan's relationship to running individual tools directly, and nothing stating that dry_run=false actually executes the plan.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.