mix_reference_recommendations

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds meaningful behavioral context: it returns ranges only conditionally ('only when alignment/readiness passes'), implying it may return nothing or an empty result when the condition fails. This is useful beyond the annotations. No contradiction with annotations.

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 that is compact and front-loads the core action ('Return bounded tonal review ranges') followed by the gating condition. No wasted words. The condition is placed at the end, which is acceptable given the sentence's brevity.

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 has an output schema, so return values are presumably documented there. The description covers the gating condition but leaves ambiguity about what 'alignment/readiness' refers to and what happens when the condition fails (empty result vs. error). Given the tool's moderate complexity and the presence of an output schema, the description is adequate but not fully complete.

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 67%: candidate_path and reference_path have descriptions, but max_seconds has only a title and default. The description doesn't explain max_seconds semantics (e.g., how it bounds the analysis) or clarify the relationship between reference_path and candidate_path beyond their names. The description adds the concept of 'alignment/readiness' but doesn't map it to specific parameters. Baseline 3 is appropriate since the schema covers most parameters.

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 specific verb ('Return') and resource ('bounded tonal review ranges') with a condition ('only when alignment/readiness passes'). It distinguishes itself from sibling tools like mix_masking_recommendations and audio_compare_files by focusing on tonal review ranges gated by alignment/readiness. However, it doesn't explicitly name a sibling alternative, and the phrase 'bounded tonal review ranges' is somewhat jargon-heavy without elaboration.

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 condition 'only when alignment/readiness passes' implies a prerequisite: the tool should be used only after alignment/readiness checks succeed. This gives some usage context but doesn't explicitly state when NOT to use it or name alternatives. The sibling list includes postfader_creation_readiness and mix_doctor, which could be related, but the description doesn't route the agent to them.

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