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

No annotations are supplied, so the description carries the full behavioral burden. It usefully discloses frame spacing (0.25 s apart) and persistence semantics ('A part keeps its last pose until moved again'), but says nothing about what happens on a static trial, whether re-keying a frame overwrites an existing pose, or what the call returns.

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 front-loaded with the gating condition and packs a lot into a short space with no filler sentences. The telegraphic style (parenthetical constraints, inline type sketches) makes it dense to parse and the final clause duplicates schema information.

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 4-parameter mutation tool with no annotations and no output schema, the description covers the essentials: applicability, frame bounds, timing, and pose persistence. The main residual gap is error/overwrite behavior and any indication of the return value.

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 75%, and the description adds real meaning beyond it: frame bounds are tied to the commission type (max_frames 16/32/64) and to timing, and the mutual exclusivity of 'frame + moves' versus 'frames' is spelled out. The trailing 'moves = {part_id: {position?, rotation?}}' largely restates the schema's own example.

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 and resource: 'set the pose of some parts at one frame' plus multi-frame keying. It is clearly distinct from part-management siblings like forge_add/forge_edit/forge_remove, though no sibling is named explicitly to confirm the boundary.

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?

It gives a firm precondition: 'Animated trials only (campaigns taille-1, taille-2, taille-3)', which tells the agent when the tool applies. It also routes between the two usage shapes (single frame + moves vs. several frames in one call). It lacks any explicit when-not or named alternative for pose-setting versus part editing.

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