qa_audio

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

No annotations, so the description carries the full burden, and it discloses non-obvious behaviors: which STT engines are used (openai | whisper), that a report file is written to qa/report.json, and that results are filtered by max_cer. It omits cost/latency, overwrite/idempotency behavior, and permissions, but the core side effects are surfaced.

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 compact sentences with zero filler; the primary action and the file output are front-loaded. Sizing is appropriate for a tool of this complexity.

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?

An output schema exists, so return values needn't be described. But with five parameters at 0% schema coverage and three of them unexplained, the definition does not supply enough to call the tool correctly (e.g., what 'run' identifies, what 'limit' caps).

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 0%, so the description must compensate, but it only hints at max_cer (the threshold) and engine (openai|whisper — and even omits the schema default 'auto'). The required 'run' parameter, 'limit', and 'segment_ids' receive no semantic explanation anywhere, leaving most inputs undocumented.

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 chain (listen back via STT, compute CER vs. TTS input, write qa/report.json, return segments over threshold) that is clearly distinct from siblings like transcribe or tts_render. It does not explicitly name the sibling it is not, but the QA-scoring angle is unambiguous.

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 second sentence implies the downstream workflow (fix pronunciation in pronunciation.json, then re-read), giving useful context for when this tool fits. However, it never states prerequisites, exclusions, or why an agent would choose this over transcribe (also STT-based) — usage is only implied.

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