save_pose_snapshot

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

The description adds substantive behavior beyond the annotations: hard capacity limits (32 per host session, 16 for native history), volatility ('invalid after restart'), and scope ('Saves ONE pose, all Point controls and read-only joint verification; no vendor assets'). With destructiveHint=true already declared, the description usefully characterizes what is stored and how long it survives, though it never explains why the operation is flagged destructive.

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?

The description is dense and front-loads the primary memory-snapshot behavior, and each sentence carries information. But it crams three distinct modes into four sentences of jargon ('topology/key guards,' 'bounded native history'), which slows identification of which parameters to use in which case.

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 6-param, zero-coverage, no-output-schema tool, the description covers limits, lifetime, and scope reasonably well. It is still missing which parameters are mutually exclusive (scene vs scene_id) and what the snapshot captures for later restore, which the paired restore_pose_snapshot sibling implies but this definition never states.

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 6 parameters, so the description must carry the load, and it does partly: it ties scene_id and character_id to the real-character mode, path to the durable .json variant, and frame as optional. It leaves 'scene' (distinct from 'scene_id'), 'root', and the mutual exclusivity of the modes unexplained, so the compensation is incomplete.

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 description names a concrete action and resource: 'Capture all local/global clip transforms and topology/key guards for a Joint subtree in host memory,' and it explicitly distinguishes three storage variants (host memory, native character history, durable .json file). It is specific enough to separate this from generic pose setters, though the three-mode framing makes the core purpose harder to extract at a glance than it should be.

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?

It gives conditional guidance ('Alternatively supply scene_id and character_id...,' 'Durable variant: scene_id, character_id, absolute new .json path'), which implies when each mode applies. However, it never references the obvious sibling restore_pose_snapshot, nor does it state when to prefer this over save_scene_copy, leaving the agent to infer the round-trip pairing.

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