set_pose

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

Annotations already declare destructiveHint=true and readOnlyHint=false, but the description adds substantial context beyond them: host transaction atomicity, automatic clip snapshot capture, before/after return, and the crucial timeout-is-unknown-outcome/read-back-before-retry rule. This is exactly the extra behavior an agent needs for a destructive write.

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?

Four tightly packed sentences, front-loaded with the core action and constraint, then prerequisites, side effects, and the retry hazard. No filler.

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 destructive 5-param nested-object tool with no output schema, the description covers transactional behavior, snapshotting, returns, and failure handling well. Gaps remain around the meaning of scene/root/space and the units expected, which the schema does not document either.

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 carry parameter meaning, and it only partially does – it implies the population and range of pose_data and mentions frame-scale constraints, but never explains scene, root, space (the local/global enum), or the unit/space semantics of the position and rotation_wxyz fields.

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+resource ('Batch-write 1-32 joints') and the mechanism ('one checked host transaction and one MCP call'), which distinguishes it from single-transform siblings like set_transform and from set_character_pose. The scoping (1-32 joints, linear FK subtree) tells an agent exactly what this tool covers.

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?

Gives explicit prerequisites: a <=121-frame, unit-scale, isolated-track linear FK Joint subtree, plus retry guidance for timeouts. It lacks an explicit statement of when to prefer a named alternative (e.g. set_transform for single joints), leaving that routing to inference.

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