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

The annotations already establish readOnly, idempotent, and non-destructive behavior, and the description adds substantial context beyond them: the transformation pipeline, the URL host allowlist defaulting to off, the both/neither input error, and the x402 payment settled only on success. This gives the agent an unusually complete picture of runtime behavior and failure modes.

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 long but every clause earns its place, covering output, pipeline, sibling differentiation, input constraints, security policy, error conditions, and cost. It is front-loaded with the core purpose before moving to constraints and billing, and remains readable despite its density.

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 six parameters, no output schema, and a nontrivial URL allowlist constraint, the description is remarkably complete. It states the return format (base64 GLB), the valid input modes, the error condition for both/neither, and the billing model. An agent given only this description and the schema can safely select and invoke the tool.

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 100%, so the baseline is 3, but the description meaningfully enhances parameter understanding: it makes the mutual exclusivity of glb_base64 and mesh_url explicit, warns that the URL host must be allowlisted, and clarifies that asset_kind triggers skinning only for avatars. The only gap is polygon_tier, whose allowed values remain unspecified.

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 names a specific verb ('Post-process'), a precise resource ('RAW generated mesh'), and an explicit pipeline (normalize → mesh-repair → rig/skin → validate → export), culminating in a clear deliverable (validated GLB as base64). It also differentiates itself from axis_process by stating it is the inline counterpart, so an agent can distinguish the tools without inspecting schemas.

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 tool explicitly frames when to use it: when an agent holds mesh bytes (e.g., fresh TRELLIS output) or has a URL, and contrasts it with axis_process, which requires a server file path. It also spells out the exact input requirement — provide glb_base64 or mesh_url, never both or neither — and the URL allowlist condition, leaving little room for incorrect invocation.

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