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

With no annotations, the description carries the full burden and does well: it discloses the billing model ($0.15 USDC via x402, charged only on success), the concrete output artifacts produced, and the engine-specific formats emitted. It omits details such as what happens when neither glb nor glbUrl is supplied and how the results are returned, but the cost/output disclosure is substantial.

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 core sentence is dense and front-loaded, but the trailing sentence about the whole GLB optimizer family (dedup, instance, weld, simplify, meshopt/draco) describes other tools rather than this one and risks implying the agent should use it for mesh optimization. Trimming that would sharpen the definition.

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 6-parameter tool with zero required parameters and no output schema, the description should clarify input selection and return shape. It explains the produced artifacts but not how they are delivered or what the tool does when the caller supplies no source, and it does not resolve the glb/glbUrl ambiguity, so gaps remain.

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 coverage is only 50%: maxHulls, resolution and maxVerticesPerHull are documented in the schema, while glb, glbUrl and engine are not. The description partially compensates by enumerating the engine targets, but never clarifies the relationship between glb and glbUrl or how to select among them, leaving the two most critical inputs undefined.

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: generate a set of convex collision hulls (V-HACD) for a model, with the exact per-engine artifacts named (Godot -convcolonly, Unreal UCX_, Unity convex MeshColliders, hulls.json, overlay). This clearly separates it from sibling glb_optimizer_optimize, _lod, _inspect and _convert, which do not produce collision data.

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?

Usage is implied rather than stated: an agent can infer this is the tool for authoring collision from the engine-specific outputs, but there is no explicit when-to-use, no prerequisite (e.g. an input GLB must exist), and no routing against alternatives such as running optimize first. The final family sentence describes sibling tooling, not this tool's usage condition.

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