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

Discloses far more than the readOnly/openWorld annotations: provider fallback order, that only DaDaScribe honors speakerNames, the asynchronous PENDING + job_id contract, what diarized=false implies about attribution, how to report `truncated`, and a prompt-injection caution. These are exactly the traits an agent cannot get 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?

Front-loads the resource and the result contract, and every clause (PENDING loop, diarization caveat, truncation reporting) carries actionable information. It is a dense run-on paragraph rather than a structured list, which slightly hurts scanability.

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-shape explanation is rightly omitted, and the async continuation path plus flag semantics are covered. The gap is connection/company resolution and the `language` parameter, which an agent would have to guess at when calling with defaults.

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 14%, so the description must compensate, and it partially does: url reuse with jobId, speakerNames labeling behavior, and agentName are all explained. But language, companyId, and connectionId are undocumented in both schema and description, and no format/example is given for the key parameters.

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: 'Returns a public video's timestamped transcript', and names the backing sources (DaDaScribe, Supadata). It implicitly separates itself from connection_get_connected_transcript by scoping to public video/podcast URLs, but it never names the sibling, so an agent still has to infer the boundary.

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?

Usage is implied by 'public video' and the PENDING/job_id retry loop, which is genuinely useful procedural guidance. However there is no explicit when-not clause and no pointer to connection_get_connected_transcript or connection_transcribe_audio for already-connected media or raw audio.

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