character_pose_apply

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

The annotations already declare the safety profile (readOnlyHint=false, destructiveHint=true, openWorldHint=false), and the description adds two genuinely new facts: the write happens in 'one checked transaction' (atomicity) and driven body Joints are exempt from the write. It still omits the key destructive detail — whether the existing target set is fully replaced and what happens to joints absent from 'pose' — plus how 'checked' failures surface and whether a checkpoint/release 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?

A single tight sentence, front-loaded with the action and scope, with the read-only carve-out correctly relegated to a trailing clause. Nothing is redundant, though the compression is heavy enough that the atomicity and joint-exemption clauses read as cryptic shorthand rather than explanation.

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 mutation with a nested 128-property payload, three undocumented parameters and no output schema, the description leaves out what gets overwritten, whether the transaction is auto-committed or must be released, how to inspect failures, and how it relates to character_pose_snapshot/character_pose_restore. The transaction and read-only hints help, but the definition is far thinner than the tool's risk profile warrants.

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 full responsibility, and it only loosely gestures at 'pose' via 'complete native Point target set'. The 'frame' and 'character' parameters receive no mention at all, and the nested pose object (max 128 properties) has no stated key/value format, leaving the caller to guess how targets map to joints.

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+resource: 'Write a complete native Point target set', with the scope qualifier 'complete' implying a full-set replacement rather than a delta, which implicitly separates it from offset/apply siblings. It does not name any alternative tool, and 'native Point target' is domain jargon an agent cannot map to a sibling such as pose_apply or character_pose_restore without guessing.

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?

Usage is only implied: the word 'complete' suggests this is for whole-set writes rather than incremental edits, and the read-only carve-out hints at what it will not touch. There is no explicit when-to-use/when-not, no prerequisites (e.g. whether a character must be selected or a checkpoint created first), and no mention of transaction_status/transaction_release as follow-ups despite the sibling list containing them.

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