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

Goes well beyond the readOnly/openWorld annotations: discloses the 25 MB refusal threshold, the output shape (timestamped segments with speaker letters), the epistemic caveat that letters are not identities, and a prompt-injection rule for transcribed speech. These are exactly the behaviors an agent cannot infer from structured fields.

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?

Five sentences, front-loaded with the action and its scope, each carrying distinct information: source types, output shape, size limit, injection rule, parameter reminder. Trailing 'Read-only.' mildly duplicates the annotation but costs almost nothing.

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?

An output schema exists so return-value explanation is optional, yet the description still usefully sketches segment/speaker format. Limits, safety, and the agentName requirement are covered; what remains thin is how companyId and connectionId select the underlying connected key, a real gap for a tool whose zero required parameters make wiring ambiguous.

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 only 20% (connectionId is the sole documented field, and only as 'UUID value wrapper'), so the description must compensate. It covers audioUrl constraints and instructs 'Pass your agent_name', but says nothing about language, companyId, or how the connection/OpenAI key is resolved.

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 public https audio file') plus concrete source examples (RSS enclosure, non-YouTube talk, shared recording). Differentiation from connection_get_video_transcript is only implied via 'not on YouTube' rather than naming the sibling, so it falls just short of the top band.

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?

'a talk that is not on YouTube' gives a real routing condition away from the video-transcript sibling, and 'one public https audio file' excludes batch/internal cases. It stops short of explicitly naming the alternative or stating exclusions like 'use connection_get_connected_transcript for already-stored transcripts'.

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