transcribe_media

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

The description reveals asynchronous behavior (queued/running states), a task-id return, and a prerequisite skill grant—context beyond the annotations (readOnlyHint=false, destructiveHint=false). It does not disclose failure modes or rate limits, but the provided context is valuable for correct use.

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 sentences, front-loaded with the main action, and every clause adds operational information. No wasteful phrasing or redundancy.

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?

Given the tool's complexity (9 params, no output schema, async behavior), the description covers the critical flow: prerequisite, rejection behavior, duplicate handling, and task-id return. It omits details about output retrieval and parameter selection, but it is sufficient for an agent to correctly invoke and handle the immediate result. Some gaps remain, so not a 5.

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 only 22%, with descriptions only for model_option_id and source_asset_id. The description adds minimal parameter semantics: it clarifies that source_asset_id refers to a project asset and that the source can be audio or video, but it does not explain diarize, quality, keyterms, num_speakers, etc. For a 9-parameter tool, this is insufficient compensation.

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 clearly states the function: 'Transcribe a project audio or video asset into a persisted transcript asset.' It uses a specific verb (transcribe), names the resource (project audio/video asset), and the result (persisted transcript asset), which distinguishes it from sibling tools like run_skill.

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 description explicitly instructs 'Call run_skill first' and warns 'This tool rejects direct calls without the active skill grant/run descriptor.' It also provides a clear when-not: 'If the result is queued or running, do not submit it again; return the task id and stop the turn.' It does not name alternatives but gives strong operational guidance.

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