weld

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

Annotations only flag destructiveHint=true; the description goes far beyond by disclosing the failure contract: an over-wide distance collapses thin faces, the call fails, changes nothing, and reports the new boundary and non-manifold edges plus a safe smaller distance. It also explains that allow_open=true welds anyway and redirects the same report into `warning`, which is exactly the kind of consequence detail an agent needs before a destructive call.

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?

Front-loaded with the core action and default, then the alternative, then the failure semantics. Dense and largely waste-free, though the single long paragraph packed with edge-case detail is slightly harder to scan than a structured layout would be.

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 destructive, no-output-schema tool this is complete: defaults, scoping, the alternative tool, the failure mode with its report contents, and the override flag are all covered. Nothing an agent needs to call it safely is missing.

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?

With 0% schema description coverage the description must carry parameter meaning, and it does for three of four: distance defaults (0.0001 m, less under 0.3 m), where's accepted forms (x, y, z, box), and allow_open's behavioral effect. Only `object` is left undescribed, though its meaning is self-evident from context.

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+resource (merge vertices) with the governing parameter (distance in metres) and the exact problem it solves (doubled vertices and seams after joining parts). It also explicitly routes away from the sibling repair_mesh, so an agent can distinguish it without opening a schema.

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?

Gives the when-to-use case ('fixes doubled vertices and seams after joining parts') and the when-not/alternative case ('for a broken mesh with holes and junk use repair_mesh'). It further distinguishes the allow_open=true variant, covering the escape hatch explicitly.

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