transcribe_voice

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

With no annotations, the description carries full burden. It discloses key behaviors: offline operation (faster-whisper, no data leaving machine), support for multiple audio formats, and optional routing side effects (saving to idea, journal, note). It lacks details on resource usage, temporary files, or whether recording is destructive, but overall provides good transparency.

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 well-structured with clear sections, parameter documentation, and examples. It is concise yet comprehensive, with no redundant sentences. Every part adds value.

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 (4 params, multiple modes, output schema present), the description covers all necessary aspects: input modes, routing destinations, model selection, and return format. The presence of an output schema is acknowledged, and the description supplements it effectively. No gaps remain.

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 description must fully compensate. It does so by explaining each parameter: audio_path vs record_seconds mutual exclusivity, route_to options with examples, model_size values and defaults. This adds significant meaning beyond the schema's bare properties.

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 tool's function: 'Transcribe an audio file or live mic recording and optionally capture the result.' It specifies the verb (transcribe) and resource (audio), and distinguishes itself by detailing offline local processing and multiple routing options, setting it apart from potential siblings like transcribe_recording.

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 clear usage context: when to use audio_path vs record_seconds, and when to use each route_to option. Examples further clarify typical use cases. However, it does not explicitly mention when not to use this tool or contrast it with sibling tools like transcribe_recording, missing a clear exclusionary guideline.

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