transcribe

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

With no annotations, the description carries the burden, and it does disclose meaningful traits: processing is local, a model file is required, and it returns both the SRT path and the text. It does not mention runtime cost, failure modes when no model is configured, or that overwrite defaults to false and will error on an existing path — notable omissions for a mutation-adjacent tool.

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?

Three tight sentences, front-loaded with the action and output type, then the dependency, then the return values and next step. Nothing is wasted and each sentence adds a distinct fact.

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 the prerequisite, the output shape, privacy-relevant behavior (local execution), and the follow-up tool, which is substantial for a 5-param tool with no annotations or output schema. It omits expected runtime and overwrite/error behavior, but the core call path is fully described.

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 100%, so every parameter including input, model, output, language, and overwrite is already documented in the schema. The description reinforces the model-file requirement but adds no syntax or format detail beyond what the schema supplies; baseline 3 applies.

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 (transcribe) and resource (a recording's speech) plus the concrete output artifact (an SRT subtitle file) and the underlying implementation (FFmpeg 8's whisper filter). This distinguishes it cleanly from siblings like extract_audio or find_text.

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?

Explicitly says to pair it with burn_subtitles to caption the video, which routes the agent to the natural follow-up step, and flags the prerequisite of a whisper.cpp model file. It stops short of stating when NOT to use it (e.g., when subtitles already exist or for non-speech audio).

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