transcribe_start

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

With no annotations, the description carries the full burden and does well: it discloses that this is an async background job that returns a job_id immediately, where output files land (<filename>.en.srt / .zh.srt / .zh-TW.srt), that translator='groq' needs a Groq key, and what force does. It does not cover auth beyond the Groq key, rate limits, or failure/error behavior.

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 core function and the async behavior, then use cases, then a clean parameter block. The parameter list is long but each entry earns its place given 0% schema coverage; wording is dense but not redundant.

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 tool with no annotations and no output schema, the description supplies the async model, the return value (job_id), the on-disk outputs, and the follow-up tool. Nothing essential for 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 0%, so the description must compensate and it does thoroughly: each of the 7 parameters (paths, language, translate, translator, model, context, force) is explained with meaning, accepted values, defaults, and practical effects (e.g. language 'zh' triggers Traditional-Chinese conversion and proofreading; context stabilizes proper-noun translation). This is far beyond what the bare schema provides.

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 (convert video/audio into subtitles or transcripts) plus the key behavioral fact that it runs as a background job returning a job_id immediately. This clearly distinguishes it from siblings transcribe_status and transcribe_list.

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 '用在：' line enumerates concrete scenarios (subtitle overlays, audio-to-text, meeting/lecture transcription, Chinese subtitle translation) that give strong positive guidance. It also routes the agent to transcribe_status for progress, though it never states when NOT to use it or contrast against the sibling tools explicitly.

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