set_ik_goal_settings

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

Annotations already declare destructive=true and idempotent=true, and the description builds substantially on that: it explains the operation runs as one undo transaction followed by an asset save, that it is a partial update applying only present fields, and that it returns changed=false/saved=false with a note when values are unchanged and save_error on save failure. These are real behavioral traits an agent cannot get from the annotations.

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?

Purpose and idempotency are front-loaded, and every sentence carries information (key formats, error outcomes, prerequisites, return shape). It is dense and long, but there is essentially no filler; the trailing Returns block is justified because no output schema exists.

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 mutating tool with a free-form nested object, no output schema, and 100% required params, the description supplies everything needed: prerequisite call, per-solver key conventions, partial-update semantics, and a full enumeration of success/unchanged/failure return fields.

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?

The schema's nested `settings` object is loosely typed (additionalProperties: true) and documents no keys, so the description is the only source of parameter meaning. It enumerates FullBodyIK snake_case keys with numeric ranges and BodyMover camelCase keys with server-side clamping, far exceeding what the schema conveys.

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 ('Set goal-specific settings for a goal connected to a solver') and explicitly scopes it as goal-level, not solver-level, which distinguishes it from siblings like set_ik_solver_settings and set_ik_bone_settings. It also names the two goal types (FullBodyIK, BodyMover) that change the expected key format.

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?

Gives a clear prerequisite ('Connect the goal first with connect_ik_goal_to_solver') and a boundary condition ('Solvers without per-goal settings return an honest error'). It does not explicitly say when to prefer this over set_ik_solver_settings, but the goal-vs-solver scoping makes the split inferable.

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