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

Goes well beyond the annotations: it discloses async job semantics, expected latency (~4 min per hour of audio), a hard 120-minute-per-file cap, a concurrency ceiling of 5 running jobs, the 2 GB size limit, and the exact billing model (1 credit per started 10 minutes, with maxDurationMinutes reserved up front and settled afterwards). The destructiveHint=true / non-readOnly profile is consistent with the disclosed credit spend.

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?

Front-loads the core operation and async behavior, then layers source rules, limits, cost, and a practical tip. Every clause carries operational information; the ffmpeg tip, while optional, protects against a costly misuse (uploading multi-GB video).

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 still covers the return contract (a jobId plus the polling tool) and all constraint dimensions an agent needs: source format, size, duration, concurrency, and cost. Nothing needed for a correct invocation 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 coverage is 100%, so the baseline is 3, but the description adds real cross-tool meaning: it explains where r2Key comes from, that url must be a direct https file link rather than a page link, and that maxDurationMinutes sizes the credit reservation and defaults to 60. The mutual exclusivity of the two source params ('pass exactly one source') is not in the schema and is a meaningful addition.

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?

Opens with a specific verb+resource ('Speech-to-text with word timestamps and segments') and names the underlying engine (ElevenLabs Scribe v2). It is immediately distinguishable from siblings like get_transcription (which polls results), generate_speech, and dub_video.

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 states the alternative flow ('returns a jobId at once; poll get_transcription (or get_job) every ~15 s') and names the upstream tools that produce valid input ('r2Key (from create_upload / import_asset_from_url)'). It also gives an exclusion ('video-platform page links are rejected') and the split-longer-recordings rule.

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