pose_release_snapshot

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

The annotations already declare destructiveHint=true, readOnlyHint=false and openWorldHint=false, so the safety profile is known. The description adds real value by scoping the destruction: what is destroyed is the snapshot handle, not scene content, which prevents an agent from mistaking this for a scene mutation. It still says nothing about whether a release is reversible, what happens to an unknown or already-released snapshot_id, or whether the underlying pose data survives.

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 short sentence with zero filler, and the qualifier that matters ("without editing the scene") is placed where it reads as a constraint rather than an afterthought. The brevity is appropriate, though it leaves little structure to hang usage rules on.

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, irreversible-sounding lifecycle operation with a required identifier and no output schema, the description omits the essentials: how to obtain the snapshot_id, what the release invalidates, and whether errors are raised for stale ids. The annotation covers the safety hint but not the operational contract, so an agent could call this and be surprised by the result.

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 single parameter is documented only by its name and length bounds. "snapshot_id" is largely self-explanatory, but the description never says where such an id comes from (presumably pose_snapshot or character_pose_snapshot) or whether it refers to a session-scoped handle, leaving the agent to infer the provenance.

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 sentence names a specific verb ("release") and a specific resource ("session pose snapshot"), which is enough to distinguish it from the snapshot/restore siblings such as pose_snapshot and pose_restore. It stops short of explicitly naming the near-twin subtree_release_snapshot, so the agent must infer the scope difference from the word "session".

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?

"Without editing the scene" implies this is a cleanup step used after a snapshot is no longer needed, rather than a way to apply or restore pose data, which is the useful discriminator against pose_restore and character_pose_restore. However, there is no explicit statement of when to call it, no prerequisite that the snapshot must exist, and no mention of subtree_release_snapshot or checkpoint_release as alternatives.

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