rig_pose_apply

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

Annotations already declare readOnlyHint=false and destructiveHint=true, so the safety profile is known, but the description adds nothing about what gets overwritten, whether existing keys or curves are lost, whether the operation is reversible, or what happens when preflight fails. The phrase 'native pose preflight and readback' hints at an internal verification step, which is the only behavioral value added, and it is left unexplained.

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 tight sentence with no filler, and the core action is front-loaded. It is compact but at the cost of clarity, so it reads as terse rather than wasteful.

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 destructive, nested-object, zero-schema-documentation write tool with no output schema and no annotations beyond the safety hints, yet the definition is one clause. It should explain the role/profile model, what targets values mean, and how verify and create_keys change outcomes.

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 six parameters including a nested targets map, so the description must compensate and largely does not. 'Profile slot order' and 'named roles' do clarify how the targets keys map to roles and how they are ordered, which is genuine added meaning, but frame, space, verify, and create_keys receive no explanation at all.

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 verb 'Write patches' plus 'named roles in profile slot order' signals a rig-pose write operation, but the wording is jargon-heavy: it never says it sets position/rotation on rig objects, and 'patches', 'roles', and 'slot order' are domain terms that are not defined. An agent can guess this is the write counterpart to rig_pose_read, but only by inference rather than by an explicit statement.

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?

There is no guidance on when to use this versus rig_pose_offset, pose_apply, character_pose_apply, semantic_pose_apply, or subtree_pose_apply, all of which are siblings that write poses. Nor does it state preconditions such as an active profile, an active scene, or whether a checkpoint should exist first.

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