subtree_pose_apply

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

Annotations already declare the destructive mutation profile (destructiveHint=true, readOnlyHint=false), so the description's added value is its mention of an implicit "scoped full-clip snapshot" and "protected unrelated-state verification" — real behavioral facts an agent should know. But these are unexplained jargon: it never says whether the snapshot must be released via subtree_release_snapshot, what happens if verification fails, or whether the edit is atomic. It also says "up to 32" joints while the schema permits 128 poses, an unacknowledged discrepancy that undermines trust in the limits stated.

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?

One compact sentence with the core action front-loaded, which is efficient. But it packs several undefined domain terms ("linear-FK", "endpoint keys", "protected unrelated-state verification") into a single clause, trading clarity for brevity.

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 four-parameter mutation tool with zero schema description coverage and no output schema, the description is too thin. It omits what the snapshot returns (a handle needed for restore/release), failure behavior, and the meaning of three of four parameters, leaving the agent under-equipped to call it safely.

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%, so the description must carry parameter meaning, and it largely doesn't. It gives no explanation of `root` (target subtree root), `frame` (timeline frame, optional), or `space` (local vs global, default global) — the local/global distinction in particular is left entirely to the enum. Only `poses` gets indirect treatment through "existing endpoint keys" and "up to 32," which conflicts with the schema's maxItems of 128.

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 concrete verb and resource ("Edit ... Joints") plus a scope (subtree, "existing endpoint keys"), so an agent knows this mutates existing pose keys rather than creating new ones. It doesn't name a sibling such as pose_apply or rig_pose_apply to explain why subtree_pose_apply is the right choice, which keeps it below 5.

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 "at existing endpoint keys" implicitly tells the agent this only works where keys already exist, which is useful usage context. However, there is no explicit when-to-use/when-not guidance and no pointer to alternatives like pose_apply, character_pose_apply, or subtree_pose_read for read access.

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