pose_offset

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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the safety profile is known; the description adds value on top by disclosing that repeated calls accumulate (non-idempotent) and that inspection is required before retrying. It still does not say what is destroyed, whether existing keys are overwritten, or whether the offset is undoable.

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 sentences, both front-loaded with the highest-value facts: what the operation is, then the accumulation/retry hazard. No filler, and the warning is placed where an agent will read it before invoking.

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, five-parameter mutation with zero schema descriptions and no output schema, the description leaves significant gaps: the effect of space, the meaning of create_keys, and what happens to values outside the supplied frames are all unstated. The accumulation and retry warning is genuinely useful but not enough to make the definition self-sufficient.

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% for five parameters, so the description must carry the burden and largely does not. The "local"/"global" space enum and the create_keys boolean are entirely unexplained, and delta being a 3-number vector, plus the frames/objects list limits, are left to the schema. Only "selected positions" loosely gestures at the objects parameter.

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?

"Offset selected positions across existing frames from their actual values" states a specific verb (offset), resource (positions), and the crucial frame-relative framing that separates it from an absolute apply. It does not name the sibling it replaces (pose_apply, rig_pose_offset), so the agent must infer the boundary from the verb alone.

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 second sentence gives real operational guidance for retries after timeouts, which is the most likely misuse path. However, it never states when to prefer this over pose_apply or rig_pose_offset, nor what preconditions exist (selection, existing frames/keys) before calling.

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