set_control

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

Annotations already declare this is a non-read-only, non-destructive, closed-world mutation, so the safety profile is covered. The description adds genuine behavioral value by disclosing the failure mode: if the plug-in hasn't exposed the parameter, the reply reports the exact parameter name and the expose step. It says nothing about value ranges, clamping, or whether the change is undoable, which matters for a mutating tool.

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?

Front-loads the capability and its key selling point ('without knowing its parameter names') before the control list, and the fallback sentence is placed last. The control enumeration is long but earns its place since there is no schema enum. No filler wording.

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 output schema exists, so return-value shape needn't be explained. For a 6-parameter mutation with zero schema documentation, the description leaves the value/normalized distinction and track targeting unexplained, which is a meaningful completeness gap even though the control vocabulary and error path are covered.

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 is 0%, so the description carries the full burden, and it documents only 2 of 6 parameters: the control enum and 'device'. Critically, it never explains 'value' versus 'normalized' — two alternate ways to set the same thing — nor what 'track_type' or 'track_index' mean, leaving a real ambiguity that would likely cause incorrect invocation.

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 a musical control') and immediately scopes it: 'on ANY device without knowing its parameter names', which implicitly separates it from the raw-parameter siblings like set_device_param. The enumeration of valid control names makes the resource concrete. It does not explicitly name the sibling it contrasts with, so a 4 rather than a 5.

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?

Usage is implied by the framing: reach for this when you know a common control name rather than a plug-in-specific parameter. The fallback path is described ('the reply names the exact plug-in parameter and the expose step'), which is helpful. However, there is no explicit statement of when to prefer set_device_param or expose_plugin_params instead, and no precondition for choosing between them.

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