set_ik_bone_settings

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

Beyond the annotations (idempotentHint/destructiveHint/readOnlyHint), it discloses the undo-transaction boundary, the asset save step, the failure contract (success=false, saved=false, save_error), the partial-update semantics, auto-creation of absent settings, the nothing-changed no-op path with a note, and the supported solver restriction. This is far more behavioral context than the annotations carry.

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?

Content is front-loaded (action + transaction, then failure contract, then partial-update semantics, then key list, then returns) and every clause carries information, including the Returns block that substitutes for the missing output schema. It is nevertheless dense and long for a 4-parameter tool, with the semicolon-chained opening sentence doing a lot of work.

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?

With no output schema and a free-form nested settings object, the description compensates fully: it documents return fields explicitly, the mutation/rollback behavior, the error paths, and per-solver key naming. Nothing an agent needs to call this correctly is missing.

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 coverage is 100% (baseline 3), but the description goes well beyond it: it enumerates the free-form 'settings' keys (rotation_stiffness, position_stiffness, limit_x/y/z, min/max, use_preferred_angles, preferred_x/y/z), gives ranges (0-1), enumerates the allowed limit values, and distinguishes FullBodyIK snake_case from StretchLimb camelCase (squashDirection) — details the schema's generic 'bone-specific fields' object cannot convey.

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 specific verb+resource ('Set bone-specific settings for a bone within a solver') and pins the scope precisely: per-bone settings on a solver inside an IK Rig, distinct from sibling tools like set_ik_solver_settings or get_ik_bone_settings. An agent can identify the operation without opening the schema.

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 clear conditions: only FullBodyIK and StretchLimb support per-bone settings and others 'return an honest error', settings are auto-created if absent, a missing bone is an error, and a value-equal update is a no-op. It does not, however, explicitly name sibling alternatives (e.g. set_ik_solver_settings for solver-level config) or state when to prefer them, so routing is left partly to inference.

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