transcribe_recording

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

The description adds useful behavioral context beyond the sparse annotations: it runs in the background ('Идёт в фоне') and its result is exposed through get_transcript. Since annotations only provide destructiveHint=false and no readOnlyHint, this async framing is valuable. It does not contradict any annotation.

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 entire description is two compact sentences with no wasted words. The purpose and trigger condition are front-loaded, and the second sentence provides the key behavioral detail (background execution and result destination). Every sentence earns its place.

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?

For a one-parameter tool with no output schema and minimal annotations, the description covers purpose, trigger condition, async behavior, and where to get the result. It is slightly incomplete only in not spelling out the semantics of id and not describing failure/error behavior, but these are minor gaps given the tool's simplicity.

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?

The input schema has one required string parameter 'id' with 0% schema description coverage, and the description never explicitly explains what id refers to. The surrounding context implies it is the recording identifier, but the description does not compensate for the missing schema documentation, leaving the parameter semantics underspecified.

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 begins with a specific verb and object: 'Заново расшифровать готовую запись' (re-transcribe a finished recording), and gives a concrete trigger condition (transcription crashed or recording process died while WAV remains). This clearly separates it from siblings like get_transcript (retrieval), list_meetings (listing), and join/leave_meeting (meeting actions).

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 states an explicit when-to-use condition: use it when the previous transcription failed but the WAV file still exists. It also points to get_transcript as the place to retrieve the result. It does not explicitly name alternatives or say when not to use it, but the intended context is clear enough.

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