live_fade

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

Without any annotations, the description carries the full burden and delivers critical behavioral details: it blocks the main thread, has side effects on mixer_device.volume, creates one undo step, may clip if exceeding unity, and enforces rejection rules for duration and target_percent. This is exactly the kind of transparency needed for a potentially destructive, blocking operation.

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 structured with clear sections: purpose, side effects, examples, edge cases. It's front-loaded with the core action, then adds necessary details. Slightly dense but every sentence adds value; could be tightened by integrating the example more seamlessly, but no wasted text.

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 7 parameters with 0% schema description coverage, no annotations, and no output schema, the description covers the essential operational context: blocking behavior, undo, clipping risk, parameter mutual exclusivity, and rejection conditions. It's complete for an agent to use correctly without needing to infer unsafe behaviors.

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 must compensate. It clarifies that exactly one of target_percent or target_value must be provided, gives default duration behavior contextually, and mentions allow_over_unity's effect. It doesn't explain curve or steps parameters, nor does it specify expected value ranges for target_value, leaving some gaps, but it covers the most critical constraint.

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 (interpolate) and resource (track's mixer volume) with target and duration. It's unique among siblings, most of which are read-only getters or unrelated operations; live_fade explicitly performs automated volume ramping, clearly distinguishing it from set_parameter_value which does a static set.

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?

Provides examples (ramping to silence, exceeding unity) that show intended use, and notes it inserts 'the first such command' suggesting it's for time-based transitions. However, it doesn't explicitly contrast with set_track_property or set_parameter_value, leaving the agent to infer that it's for smooth fades rather than instant changes.

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