transcribe

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

No annotations exist, so the description bears full responsibility for disclosing behavior. It notes '[writes]' (suggesting mutation), requires a Whisper model, and mentions variable runtime. However, it fails to clarify side effects (e.g., file creation?), error handling, idempotency, or safety aspects. This leaves significant gaps in behavioral understanding for an agent.

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 three sentences long, front-loading the purpose first, then parameter clarification, then prerequisite and performance note. Every sentence contributes distinct value with no redundancy or fluff.

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 sibling tools (list_files, download, get_transcript), the description fits well into a transcription workflow. It explains the prerequisite (Whisper model), the path convention, and the time cost. Minor omission: it could explicitly state that the file must already be downloaded via the download tool, but the phrase 'downloaded file' and the path example imply this. The output schema exists, so return value documentation is not needed. Overall very helpful for an agent.

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%, requiring the description to explain all parameters. It adequately explains the 'name' parameter (downloads-relative path with example), but entirely omits the 'language' parameter (schematype: string, default: ''). With only one of two parameters described, the description adds only partial value beyond the 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 clearly states the action: 'Transcribe a downloaded file locally with Whisper and return the text.' It specifies the verb (transcribe), resource (downloaded file), method (Whisper locally), and output (text). This distinguishes it from sibling tools like get_transcript (which likely retrieves existing transcripts) or list_files/download.

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 provides context: it requires a Whisper model set in settings and warns that it can take a while. This gives implicit usage guidance, but it does not explicitly state when to use this tool over alternatives (e.g., get_transcript) or list conditions where it should not be used. The guidance is adequate but not comprehensive.

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