restore_pose_snapshot

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

Annotations already declare destructiveHint=true and openWorldHint=false, so safety is partly covered; the description adds substantial beyond-schema behavior: identity/topology/key-layout guards, full readback, refusal of changed track structure and external scene edits, bounded native Undo with full-state verification, and joint verification before commit. These refusal/verification semantics are exactly the kind of context an agent needs before invoking a destructive restore.

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?

Front-loaded with the core verb and resource, which is good, but the body is telegraphic fragment-speak (semicolon-separated clauses, mode-hopping) rather than structured prose. Several clauses about guards could be compressed once and referenced, so the density is not fully earning its place.

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 5-param, no-output-schema, destructive tool the description covers the important refusal and verification behavior, but it omits the meaning of snapshot_id and scene and does not state what a successful restore returns or how failures surface. Adequately informative on behavior, incomplete on the calling contract.

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 the parameter burden. It does explain scene_id, character_id, and path for the durable variant, but never explains snapshot_id (the primary handle for the clip-snapshot mode) or the 'scene' parameter, leaving two of five parameters semantically opaque.

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 specific verb and resource ('Restore clip transforms from an opaque host-memory snapshot') and explicitly distinguishes itself from the sibling save_pose_snapshot's inverse operation and from a general scene undo. The three execution modes (clip snapshot, character/scene_id, durable path) are named, though the bundling makes the core purpose slightly harder to extract.

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?

Offers exclusions ('Not a general scene undo', 'Not a whole-clip backup') and conditional routing ('For character snapshots supply scene_id'), which is real guidance. However, the mode selection is tangled – it never clearly states when to use snapshot_id vs scene_id vs the durable path variant, so the agent must infer the mapping.

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