semantic_pose_apply

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

Annotations already declare readOnlyHint=false, destructiveHint=true, and openWorldHint=false, so the mutation/destruction profile is known. The description adds genuinely useful behavior beyond that: omitted slots are merged rather than cleared, and the resulting keys use LINEAR interpolation. It still does not state what happens to existing keys at that frame, whether the merge overwrites conflicts, or what authorization/selection state is required.

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?

Two short sentences with no filler, front-loading the operation before the side effect of creating LINEAR keys. The density is good; the only cost is that the brevity comes partly from unexplained jargon rather than true precision.

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, no-output-schema mutation with a nested object parameter at 0% schema coverage, the description leaves too much unspecified: the shape of the pose payload, the meaning of "real native targets," per-parameter defaults, and overwrite behavior for existing keys. What is present is accurate but insufficient for confident invocation.

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 three parameters, so the description carries the burden. It partially explains the pose object ("named Point slots", omitted slots merge with native targets) but says nothing about frame (default? current frame?) or character (defaults to active character? required to disambiguate?), and the nested pose object's expected keys are never enumerated.

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?

Names a concrete verb and resource ("Patch named Point slots at one existing frame") and mentions creating LINEAR character keys, so the operation is identifiable. However, the terminology ("Point slots", "real native targets") is domain jargon and the description does nothing to distinguish it from siblings such as semantic_pose_apply_sequence, semantic_pose_offset, rig_pose_apply, or pose_apply. Differentiation is left entirely to the name.

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 explicit when-to-use guidance and no mention of alternatives. An agent cannot tell from the text whether a sequence of frames should use semantic_pose_apply_sequence or whether an offset application needs semantic_pose_offset. The only implied constraint is "one existing frame," which hints at single-frame scope but does not route the agent.

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