match_reference

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

Annotations only say it is not read-only and not destructive; the description adds the useful specifics that apply=True creates an EQ Eight device named "Ref Match" on the master and where it lands (track_type/track_index), plus the strength and max_db caps that bound the change. It does not say what happens if a "Ref Match" device already exists (replace, duplicate, skip) or whether the operation is undoable, which is the main remaining behavioral gap 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?

Two sentences, zero filler, and the core comparison behavior is front-loaded before the optional write path. The parenthetical enumerating the compared dimensions and the inline ranges for strength and max_db are dense but each earns its place.

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?

For a 7-parameter analysis-plus-mutation tool, the definition covers the decision-relevant surface, and an output schema exists so return values need no explanation here. The gaps are the collision behavior on repeated apply calls and any file/format expectations for the two path parameters, both of which an agent would otherwise have to guess.

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?

With 0% schema description coverage across 7 parameters, the description must carry the load and does for most of them: apply, strength (fraction 0..1 of the difference), max_db (cap on move size), and the track_type/track_index destination. mix_path and reference_path are only implicitly characterized as the bounce and the reference song, with no hint about accepted formats or whether paths must point to existing files, so it falls short of full coverage.

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 concrete verb (compare) and both resources (a bounce, a reference song), then names exactly what the comparison yields and what the optional write path does. An agent can distinguish this from generic device/effect siblings like add_effect or build_chain without opening the schema.

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 makes the analyze-only vs apply branch clear through the apply flag, which implies when to use each mode. However, it never states prerequisites (e.g., the mix must exist as a bounced/rendered file), nor names an alternative tool or a when-not-to-use condition, leaving real routing decisions to inference.

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