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

With no annotations, the description carries the full burden and does so: credit consumption with credited/re-import warning, 1GB/3-hour limits, stateless in-memory processing (LGPD, never persisted), the fact that the result is NOT stored, and the instruction to relay the entire response. This is exactly the behavioral context an agent needs before spending credits on an irreversible call.

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?

Front-loaded with purpose and usage before the parameter and behavioral detail, and the IMPORTANT warning is correctly placed last. The MIME-type and language enumerations are long, but they are the only documentation of those constraints anywhere, so they earn their space rather than being padding.

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 cost-incurring, stateless tool with no output schema, the description enumerates every returned field (id, language, language_confidence, duration_seconds, text, dialog, audio_events, event_types, word_count, input metadata), so the agent knows what to expect and relay. Nothing needed to call it correctly or handle its result is missing.

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 0%, so the description must compensate and does: file_base64 is defined as base64 of the file bytes with filename optional, model is documented as defaulting to the only supported value, language is documented with the full accepted code list and auto-detect behavior, and client_reference_id is given a charset, a 60-char cap and the explicit note that it is echoed verbatim and is not an idempotency key.

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 and resource ('Transcribes one uploaded audio file into text') plus the differentiating capabilities (speaker diarization, timestamped audio events) and the exact return shape. An agent can immediately tell this apart from siblings like risk_audit or extract_whatsapp.

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?

Gives clear context for use ('when a recording must become text for analysis, review or storage of the transcript') and the scoping constraint that it handles a single file. It does not name any alternative tool or state when NOT to use it, but the sibling set offers no competing transcription option, so the omission is minor.

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