set_parameter

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

With no annotations, the description carries full burden and excels. It discloses that parameter values are normalized, not displayed units; that the curve from 0..1 is nonlinear and device-specific, illustrated with a concrete example; that quantization can cause read-back to differ; and that such discrepancies are reported as clamps. It also states the return format. These are precisely the kind of behavioral facts an agent needs to avoid silent mistakes.

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 long but every sentence earns its place. It is structured with clear sections: purpose, args, returns, and a note. The note's density is justified because silent factor-of-30 errors and quantization clamps are critical for correct use. No filler or redundant repetition 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?

Given the tool's complexity (5 parameters, normalization, nonlinear mapping, quantization, no annotations) the description is remarkably complete. It covers parameter addressing, kind handling, return content, precondition to check min/max, nonlinear curve caveat, and quantization behavior. An agent has everything needed to select and invoke the tool correctly.

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 is0%, so the description must compensate — and it does. It explains each parameter: track is interpreted in song. tracks or song.return_tracks and ignored for master; device is an index within the chain; parameter is a string index or glob; value is target value; kind accepts 'track', 'return', or 'master'. This adds semantic depth far beyond the bare schema types.

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 opens with a specific verb and resource: 'Set a device parameter by numeric index or name/glob and verify read-back.' This clearly distinguishes it from siblings like lom_set (generic LOM setter) and set_mix (mixer). The method of addressing parameters is also explicit, leaving no ambiguity about the tool's function.

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 gives explicit guidance on how to use the tool: how to specify track, device, parameter, value, and kind, including the special case of master. It also advises using 'describe' to read min/max instead of assuming a range. However, it does not explicitly state when to prefer this tool over alternatives like lom_set or set_mix, or when not to use it. That keeps it one step below a fully explicit usage guidance.

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