nass_start_transcription

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

No annotations are provided, so the description carries the full burden. "Queue" hints at an asynchronous job, but the description never states that the result must be retrieved via nass_job_status, nor does it mention auth, rate limits, or typical latency. The mode semantics are disclosed well, which partially compensates.

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-loaded with the purpose in the first clause, then the mode taxonomy. The mode list reads as one dense run-on sentence but every clause carries needed definitional information; nothing is wasted.

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?

There is no output schema and no annotations, so the description should explain the async contract (that this returns a job handle to be polled via nass_job_status) and ideally the language default. Mode semantics are complete, but the lifecycle a caller must follow is left for the agent to infer.

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 0% and enums are absent, so the description is the only source for the mode vocabulary (auto/captions/audio/verify) — and it explains all four with a clear recommendation. The language parameter (default 'ar') goes unmentioned, and video_url is left to the schema, but the critical enum-like parameter is fully covered.

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+resource ("Queue a YouTube transcription") that clearly distinguishes it from sibling read/poll tools like nass_get_transcript and nass_job_status. It does not, however, differentiate itself from other 'start_*' siblings (nass_start_local_file, nass_start_audio_download), leaving the YouTube-vs-local-file boundary implicit.

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?

Gives concrete when-to-use guidance for the mode argument ("prefer 'audio' for no-captions videos or when verifying quoted speech"), which is directly actionable. It stops short of naming alternatives (e.g., when to use nass_start_local_file instead), so no explicit exclusions.

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