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

With no annotations, the description carries the full transparency burden. It discloses the API key requirement, metered billing, and the 4MB limit—key operational traits beyond the basic function. It does not mention return format or error behavior, but the disclosed constraints are meaningful.

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 sentences, each earning its place: purpose, key requirement/billing, and size limitation with fallback. The content is front-loaded and free of filler.

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 absence of an output schema and annotations, the description covers critical operational context (auth, metering, size limit). It stops short of describing return values or when to choose streaming over batch, but for a transcription tool it provides a solid operational picture.

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 the baseline is 3. The description adds no parameter-specific detail beyond what the schema already explains (e.g., audio_base64, dialect, context). It does not need to because the schema is thorough.

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 uses a specific verb+resource: 'Transcribe Kurdish audio (Sorani or Kurmanji) to text.' It clearly differentiates from siblings like synthesize_speech (opposite direction) and start_streaming_transcription (streaming vs. file-based).

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 concrete usage context: it requires an STT API key, is metered per minute, and has a 4MB size limit. It also names an explicit alternative for larger files (direct API call). However, it does not contrast with the sibling start_streaming_transcription, so some guidance gap remains.

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