export_glb

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

With no annotations provided, the description carries the full burden. It does disclose the return value ('Returns the absolute path and file size') and the self-contained packaging, which is useful. But it does not disclose side effects on the Blender scene, overwrite behavior, failure modes (e.g., no objects/selection), or prerequisites such as needing a selection or existing objects. Adds some value but leaves behavioral gaps.

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?

Three tight sentences with zero filler: the core function is front-loaded, followed by the use-case rationale and the return value. Every sentence earns its place.

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?

This is a 12-parameter export tool with no annotations and no output schema, so the description should carry substantial guidance. It covers the return format but does not explain parameter tradeoffs, prerequisites (objects must exist or be selected), or failure cases. A one-line format summary is thin for a tool this complex.

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 50%, leaving overwrite, export_uvs, export_normals, apply_modifiers, export_materials, and export_animations undocumented. The tool description contributes no parameter guidance at all — it never mentions any of the 12 parameters or their tradeoffs (draco compression, tangents for normal maps, animations). At half coverage the description should compensate but instead adds zero parameter semantics.

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 ('Export to a single self-contained .glb file') and grounds the format in a concrete use case ('usual choice for game engines and web viewers'), which differentiates it from the sibling exporters (export_gltf, export_fbx, export_obj) without naming them. An agent can tell what it does and when it is the right format.

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 'usual choice for game engines and web viewers' line is an implicit usage cue, implying use when targeting those consumers and implying GLB's self-contained nature over GLTF's potentially external files. However, it never names an alternative explicitly, states when NOT to use it, or contrasts with export_gltf, the closest sibling. Guidance is implied, not stated.

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