poly_weld_vertices

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

Annotations already declare destructiveHint=true and readOnlyHint=false. The description adds behavioral context beyond that: threshold sensitivity, risk of over-welding, and scene-unit guidance, which help the agent predict operation outcomes.

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?

Bilingual but compact: the first sentence states the operation, and the second adds only useful threshold behavior. No wasted words and the core semantics are front-loaded.

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?

With annotations covering destructiveness and the schema documenting vertices/objects, the description is sufficient to invoke the tool. Minor gaps are the lack of a stated default threshold when omitted and no explanation of return/result behavior, but these are not critical for this imperative operation.

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 covers all parameters (100%), so baseline is 3. The description adds genuinely useful threshold semantics by explaining units (scene units), safe ranges (0.01~0.1), and failure modes for too-small/too-large values.

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?

Description states a specific verb and resource: 'Weld (merge) a batch of vertices within a threshold.' The 'batch' and 'within a threshold' qualifiers distinguish it from the sibling poly_target_weld, which is a single-target weld.

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 clear contextual guidance on threshold choice ('too small may weld nothing; too large may merge unrelated vertices') but does not explicitly state when to prefer this tool over alternatives such as poly_target_weld or poly_remove_vertices. Usage is implied by the 'batch' wording rather than explicitly contrasted.

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