bmesh_operation

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

No annotations are provided, so the description must fully disclose behavior. It mentions 'precision' and 'without operator overhead' but omits important details: whether the tool modifies the mesh in-place, error conditions (e.g., if mesh_name doesn't exist), permission/context requirements, or side effects. The operation descriptions partially cover behavior (e.g., remove_doubles merges vertices) but are insufficient for a mutation tool.

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 well-structured with a clear introduction, then a bulleted list of operations. The listing is necessary due to the many variants, but it is somewhat long. It front-loads the main purpose. Minor redundancy: 'quads_to_tris — same as triangulate' could be omitted or merged. Overall efficient for the complexity.

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?

Given the tool's complexity (16+ operations) and the presence of an output schema (reducing need to describe returns), the description covers most required aspects: parameters, operations, and their effects. It lacks prerequisites (e.g., mesh must exist, object selection) and error handling, but overall is sufficiently complete for an experienced user.

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 input schema has 0% description coverage, making the description the sole source of parameter meaning. The description provides detailed explanations for the 'operation' parameter (list of enums with effects and optional params) and specifies the format for 'params' (JSON). mesh_name is self-explanatory. This adds substantial value beyond the schema.

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?

Purpose is clearly stated: 'Execute precision BMesh operations on a mesh'. It specifies the verb (execute), resource (mesh), and context (BMesh direct manipulation without operator overhead). The distinct nature of low-level mesh editing is implicit, distinguishing it from sibling tools like boolean_operation or bevel_edges which are higher-level.

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 provides a comprehensive list of specific operations with brief explanations, which guides usage. However, it lacks explicit when-to-use vs alternatives (e.g., merge_by_distance vs remove_doubles). The context is clear but could improve by directly comparing with similar tools in the sibling list.

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