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

With no annotations provided, the description carries the full burden of behavioral disclosure. It discloses the processing state (status=processing), the need for polling, the processing time ratio, and the conditional presence of speaker labels based on diarize=true. This is transparent about the tool's non-immediate response and conditions, though it does not mention error cases or side effects (which are minimal for a read-only fetch).

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 concise and well-structured: two sentences (three in the original Russian) that front-load the main purpose, then add polling guidance and timing. No redundant information; every sentence contributes actionable context.

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 simple polling tool with two parameters and no output schema, the description covers everything an agent needs: what it returns, how to handle the processing state, the expected duration, and the condition for speaker labels. It is complete for correct invocation and interpretation.

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 100%, so the schema already documents job_id and format, including the default text format. The description adds value by explaining that speaker labels only appear if diarize=true was passed at transcription time, which is a behavioral condition not in this tool's schema. This extra context helps the agent understand output variability, though it's not strictly about parameter syntax.

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 returns task state by job_id, and when ready, the transcript text with timestamps and speaker labels (if diarize=true). It uses a specific verb ('возвращает') and resource (task state/transcript), and implicitly distinguishes from siblings like list_transcripts by requiring a specific job_id for a single transcript retrieval.

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 gives explicit polling guidance: while processing it returns status=processing, so call again after a pause. It also mentions the timing (an hour of audio takes ~1.5 minutes). However, it does not explicitly mention alternatives or when not to use this tool versus list_transcripts or search_transcripts, so it's clear on how to use but not on when to choose this over others.

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