make_host_sample

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

With no annotations, the description carries the full burden, and it does substantial work: it discloses the bone hierarchy (root > hips > chest > head, legs, arms), the exact clip set with durations and loop types (idle 2.4s loop, walk 1.0s loop, win 1.2s one-shot), and the add-on layers produced. It omits filesystem behavior such as whether out_dir is overwritten or what file format is emitted.

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?

A single dense sentence that front-loads the core purpose ('Procedural minimal biped host for attach_rig') before the supporting detail. The nested parentheticals for clips and parts are information-dense but make the sentence heavy; still, no filler sentences.

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 2-param procedural generator with no annotations, no output schema, and 0% schema coverage, the description supplies a rich picture of what is generated (bones, clips, parts). The main gap is the semantics of the required out_dir output location and any file-writing behavior, which nothing else in the definition covers.

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 0%, so the description must compensate. It fully documents the `parts` parameter by enumerating all accepted values (ears, tail, wings, horns, snake_hair, mermaid, fur, glow, digitigrade) and the default (ears, tail, wings), which is strong. The required `out_dir` parameter receives no explanation at all, leaving half the parameters undocumented.

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 states a specific verb+resource: a procedural minimal biped host for attach_rig, and enumerates its concrete contents (bone chain, clips, part layers). It is distinguishable from generic sample makers, though it never explicitly names or contrasts with the very similar make_biped_sample sibling.

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 phrase 'for attach_rig' implies this sample is meant as a host to be followed by attach_rig, which is useful implied context. However, there is no explicit when-to-use guidance and no indication of when to prefer make_biped_sample, make_sample, or other sibling generators instead.

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