export_glb

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

With no annotations at all, the description carries the full behavioral burden and does so well: it states the axis convention and triangulation, the world-origin scaling semantics, that the scene is restored afterwards, that the scale is written as node scale, and that max_texture_size rewrites copies inside the GLB while on-disk images stay unchanged. It even hints at return payload structure ('The answer has textures: count, bytes, and name, size and bytes').

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?

It is long but dense – nearly every sentence adds a distinct fact (units, side effects, compression caveat, texture budget heuristic). The core purpose is front-loaded, though the texture-size discussion drifts toward an aside for a tool that does much more.

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 10-parameter mutation tool with no annotations and no output schema, the description covers side effects, scale semantics and return hints well, which is the hard part. It remains incomplete on five parameters and on whether an existing file at `path` is overwritten, which is the main residual risk for an export 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 description coverage is 0% across 10 parameters, so the description must compensate, and it only partially does: it explains draco (needs the Draco decoder), influences (bones per vertex), scale (world-origin multiplier with a worked example) and max_texture_size (pixels on longer side, with a size/quality tradeoff). skins, tangents, animations, apply_modifiers and path are left entirely to the bare 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?

The opening sentence gives a concrete verb and resource ('Write a GLB of the named objects (with children), or of all visible geometry'), so the operation and its scope are unambiguous. It does not name or contrast with the nearby siblings (import_glb, inspect_glb, save_blend), so an agent must infer the boundary from the name alone.

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 by the game-engine framing ('the bones per vertex that the game engine reads', 'the game needs the Draco decoder') but there is no explicit when-to-use, when-not-to-use, or alternative routing. An agent can infer it exports for a game runtime, but nothing steers it away from inspect_glb or save_blend.

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