blender_auto_validate

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

Annotations declare readOnlyHint=true and destructiveHint=false, but the description states that it can 'repair' problems when apply_fixes=true. This contradicts the readOnlyHint, as fixing is a mutation. The description does not disclose potential side effects, irreversibility, or the need to save the file, which are critical for a write-capable tool. This is an annotation contradiction.

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 concise (two sentences) while packing substantial information: the tool's purpose, optional fixing capability, and the problem domain it addresses. It is front-loaded with the core action and context, making it easy to scan.

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 tool with no output schema, the description does not explain the structure of the audit report beyond the response_format parameter. It also omits key behavioral details: what happens when fixes are applied (e.g., whether the .blend file is saved), and the meaning of 'unambiguous' in practical terms. The complexity is moderate, so more explicit guidance on expected outcomes would improve completeness.

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?

The schema already covers all parameters with descriptions (100% coverage), including apply_fixes and quick. The description adds context by mentioning that fixes are applied to 'problems that have an unambiguous fix', which clarifies the scope of apply_fixes, but otherwise relies on the schema for parameter meaning. This meets the baseline for high schema coverage.

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 states the tool audits a generated model end-to-end and can optionally repair problems with unambiguous fixes. It lists the specific domains covered (topology, UVs, materials, scale, naming) and positions it for the 'is it usable' question, distinguishing it from generic validation or mesh analysis tools.

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 when to use it ('I just generated this, is it usable'), which guides the agent to invoke it for end-to-end validation after generation. It does not explicitly exclude alternatives like blender_validate or blender_find_problems, but the focused scope of repairing unambiguous fixes and covering multiple aspects makes the usage context clear.

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