Stage Control Map

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

With no annotations, the description carries the full burden and does well: it discloses the reply payload {person, drives, presets, pins}, the emitted events (control_map, control_set, control_bound), and the destructive-ish effect of clear=True (every part returns to the built-in map). It omits permission/authorization requirements and whether replacing drives without clear merges with or overwrites existing parts.

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?

Dense but front-loaded: the read-vs-set framing comes first, then per-parameter semantics, then the save alternative and return/event info. No filler sentences, though the compressed punctuation ('drives= a list...') occasionally costs a re-read.

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 5-parameter mutation-capable tool with no annotations, the description supplies the mode semantics, the reset behavior, the cross-tool routing, and the emitted events; the reply shape is stated even though an output schema also exists. What remains missing is minor and inferable from the required-parameter list.

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 0%, so the description must compensate, and it explains three of five parameters plus the nested item shape for drives ({part, mode, joint, at, scale, touch}) and the implicit auto-apply rule for a 'default' preset. The 'scene' parameter is never explained and 'person' is only implied by 'a person's control map'.

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 pair (read or set) on a specific resource (a person's whole control map) and even names the underlying page command. It routes to the sibling that handles the adjacent job (stage_actor_map_save) rather than leaving the agent to guess among the many stage_* tools.

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?

The description enumerates the mode-selecting conditions well: 'With nothing else' reads, preset= applies a saved map, drives= applies a list in order, clear=True resets first, and saving goes to stage_actor_map_save. It does not differentiate from the close sibling stage_control_set, which an agent could plausibly confuse with this one.

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