fl_set_mixer_stereo_separation

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

Annotations already cover the safety profile (readOnlyHint=false, destructiveHint=true, idempotentHint=false). The description adds a genuinely useful behavioral trait beyond annotations: the tool reports FL's 'later-tick readback,' implying the write may not be reflected immediately and the returned value can diverge from the requested value — a non-obvious timing nuance an agent should know before trusting the result. It doesn't contradict the write/destructive annotations, so no contradiction is flagged.

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?

A single sentence with two clauses, zero filler, and the essential action front-loaded before the readback caveat. Both clauses carry distinct useful meaning: the operation and the verification behavior. There is no wasted wording or redundancy with the schema.

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 tool is a mutation with a concurrency guard and a reported readback, and it has an output schema to describe return values. The description mentions the readback but leaves ambiguity about why a later-tick read could differ and what the implications are. Given the openWorldHint and destructive annotations, slightly more behavioral context (e.g., what failure or divergence implies) would improve completeness, but the schema and annotations cover the mechanics, making this adequately minimal rather than deficient.

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 100%, so the schema fully documents all five parameters, including the concurrency-guard semantics of session_fingerprint and the master-track gating of allow_master. Per the baseline rule, a 3 applies when the schema does the heavy lifting. The description adds no parameter-specific meaning, which is acceptable here since nothing is missing from the schema.

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 uses a specific verb ('Set') with a specific resource ('stereo separation') and adds a non-obvious twist: 'report FL's later-tick readback,' signaling that the actual applied value may be verified asynchronously. The name alone distinguishes it from the many sibling mixer setters (volume, pan, mute, solo), and while the description doesn't explicitly contrast with siblings, it clearly states the operation. The readback clause adds definitional value beyond the name.

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?

No when-to-use guidance exists. The description offers no context on when to prefer this tool over fl_set_mixer_pan, fl_set_mixer_volume, or fl_set_mixer_send. There are no exclusions, alternatives, or conditions stated in the description. Some usage nuance is embedded in schema fields (allow_master is 'Required to target mixer track 0'), but the description itself leaves the agent to infer selection criteria, which is inadequate given the dense sibling set.

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