transcribe_audio

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

Goes well beyond the annotations: it discloses the download-then-upload data flow (audio leaves the system to an external service, consistent with openWorldHint), that the transcript is cached, and that the WhatsApp account is not modified. It adds a security-relevant instruction to treat the transcript as untrusted third-party content, plus the exact return shape, none of which is derivable from the annotations.

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, then mechanism, then alternatives and preconditions — no filler sentences. The first sentence is a long semicolon-chained run-on that could be split for readability, which is the only reason it is not a 5.

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?

Despite no output schema, the description enumerates the returned JSON fields, covers configuration and read-only-mode availability, names the alternative tools, and flags the prompt-injection risk. For a three-parameter tool that ships audio to an external service, nothing an agent needs before calling 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 coverage is 100% and every parameter already carries a description (JID formats, ISO 639-1 hint, audio message id). The description only adds the provenance hint for message_id ("as returned by list_messages"), which is useful but marginal — the baseline 3 is appropriate when the schema does the heavy lifting.

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 ("Transcribe an audio message") and immediately names the mechanism (configured speech-to-text service). The clause distinguishing it from download_media ("if you only need the file") lets an agent separate the two siblings without opening either schema.

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 explicit routing: use list_messages to obtain the message_id, use download_media when only the file is wanted. It also states the preconditions that gate invocation — WHATSAPP_MCP_TRANSCRIBE_URL must be set and the tool is unavailable in read-only mode — which is exactly the when-not guidance an agent needs.

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