compare_transcription_engines

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

No annotations are provided, so the description carries the full burden: it discloses the side effects (writes comparison.json and comparison.html to output_dir, self-contained HTML with audio player and seek buttons) and the default windowing behavior. It does not mention cost/API implications of engines like assemblyai or runtime expectations for two passes over the sample.

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?

Three sentences, front-loaded with purpose, then interpretation caveat, then outputs. Every sentence earns its place; the 'neither engine is assumed correct' clause is short and materially changes how results should be read.

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?

With no output schema, the description does the necessary work of naming the two artifacts produced and their nature. It could go further by describing what comparison.json contains (per-window disagreement records), but nothing required to invoke the tool correctly is missing.

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 already documents all nine parameters including enums and defaults. The description only reinforces the 20-second window default, adding no new parameter meaning beyond the schema — the baseline of 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?

States a specific verb and resource (transcribe a file with two engines and report disagreement), plus the scope constraint that it compares engines rather than measuring accuracy. An agent can immediately distinguish it from transcribe_podcast, which produces a single transcript.

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?

Explicitly frames when this tool is appropriate by negating the wrong use case ('not accuracy against a ground-truth transcript', 'neither engine is assumed correct'), which prevents misuse of the output. It stops short of naming the alternative (e.g. transcribe_podcast / parse_transcript) for when a single transcript is wanted.

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