set_looper_state

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

Annotations already mark destructiveHint=true, but the description adds crucial detail: Record/Overdub can mutate captured audio and cannot be rolled back by restoring a parameter value. It also discloses that the result reports the immediately observed state and match status, not an audible or quantized-boundary outcome, and explicitly denies beat-scheduled execution. This goes well beyond the annotations, providing full behavioral disclosure.

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 multi-sentence but every sentence contributes: it states the purpose, explains execution semantics, warns about destructive behavior, and clarifies limitations. It is front-loaded with the core action and the enumerated states, and the warnings are placed logically. Slightly longer than necessary but well-structured and efficient.

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 (7 parameters, destructive, no output schema), the description is remarkably complete. It explains what the result reports (the observed state and match status), covers the destructive nature of Record/Overdub, warns about quantization, and implicitly describes the two-step plan/confirm flow. There is no output schema, so the description correctly shoulders the burden of describing the return value. Nothing essential is missing for correct invocation.

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 86%, so the schema already documents most parameters thoroughly. The description adds a bit of context: it clarifies that 'Plan or request' maps to dryRun behavior, and it explains that targetState is one of the four enum values. It also indirectly explains expectedStateVersion by mentioning 'rechecks the complete Looper, routing, and transport snapshot before writing State.' However, the description doesn't add much beyond the schema, so a baseline 3 is appropriate.

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 states a clear, specific action: planning or requesting one of exactly four native Looper states (Stop, Record, Play, Overdub). It names the verb and the resource precisely, leaving no ambiguity about what the tool does. Though it doesn't explicitly contrast with sibling tools, the unique scope (looper state) and the exact enumeration distinguish it from transport or mixer setters.

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 clear context for when to use it: it's for looper state changes, and it explicitly warns that beat-scheduled execution is not guaranteed and that native quantization behavior must be verified separately. It also implies a two-step plan/confirm flow via 'Plan or request' and mentions the dryRun and confirmationToken parameters, guiding the agent on proper usage. It does not name alternatives, but the scope is narrow enough that this is sufficient.

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