rig_profile_create

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

The annotations already declare readOnlyHint=false and destructiveHint=true, so the agent knows this is a write operation. The description usefully adds that the profile persists in the workspace and is scoped to the saved scene and its topology. However, it never says what the destructive behavior affects, namely whether an existing profile with the same name is replaced, or how the 'overwrite' flag changes that.

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?

The description is two sentences with no filler: the action comes first, and the persistence scope follows. The only mild imprecision is 'your own', which is slightly colloquial for an agent-facing definition.

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?

The description is adequate for a schema with a required nested object, a name field, and an overwrite flag, and it supplies the one semantic hint, which is role-to-control mapping, that the bare schema cannot convey. The description of a destructive mutation is still incomplete about the overwrite behavior and the failure conditions, such as an unknown native control or an unsaved scene, and the definition provides no output schema to compensate.

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 description coverage is 0%, so the description must carry the burden of explaining the parameters. The sentence 'Bind your own body, hand, finger or prop roles to exact native controls' explains what the nested roles map means, namely role names mapped to lists of native control names, which is the most valuable information about the parameters. It still leaves the 'name' and 'overwrite' parameters completely unexplained.

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 action ('Bind ... roles to exact native controls') and a specific artifact ('Stores a workspace profile tied to this saved scene and topology'). That distinguishes it from rig_profiles_list and rig_profile_read, which by name only read profiles, though the term 'native controls' is left unexplained.

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?

There is no explicit when-to-use guidance, no mention of prerequisites beyond the vague clause 'tied to this saved scene', and no routing to alternatives such as rig_profile_read or rig_pose_apply. The phrase 'your own ... roles' only hints that this is for custom bindings; the agent must infer that the profile should already exist and that the scene should have been saved.

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