transcribe_selection

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

No annotations are present, so the description carries the full burden. It discloses 'Requires separate setup', 'Runs in BACKGROUND - returns a job_id immediately', and '[EXPERIMENTAL]', which are useful behavioral traits. It does not explain how to retrieve the transcription result or what happens if no region is selected, leaving a notable gap.

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?

The description is compact and front-loaded with the experimental warning and core scope before moving to prerequisites and parameters. Every sentence contributes, though the Args formatting uses a little extra space.

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?

The description covers setup, scope, background behavior, and parameter semantics, which is good for a 3-parameter tool. However, with no output schema or status-tool reference, an agent doesn't know how to retrieve the result or verify success; mentioning a status-checking sibling would make it complete.

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%, but the description's Args section fully compensates: model_size lists valid model choices, language explains ISO codes or None, and task lists 'transcribe' or 'translate'. This adds the semantic meaning entirely absent from the raw schema.

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 opens with 'Transcribe only the currently selected audio region', naming a specific verb, resource, and scope. It clearly distinguishes from broader transcription tools by emphasizing 'only' the selected region, though it does not name sibling alternatives.

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?

It gives a concrete prerequisite: 'Select a region first, then call this tool' and notes background execution, which implies the right workflow. However, it does not explicitly compare against siblings like transcribe_audio or transcribe_to_file, nor state when not to use it.

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