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

Beyond the annotations it discloses artifact lifetimes (private links 15 minutes, temporary audio/presentation files expire in seven days, report videos retained while the source remains available), that repeated requests return the saved video, that text masking defaults on, and that unredacted audio requires explicit researcher instruction because speech is not anonymized. This tells the agent what persists, what expires, and what consent gate applies — none of which the annotations convey. Minor tension exists with idempotentHint=false, though the required idempotency_key parameter makes the caching language reasonable.

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?

It is dense but nearly every sentence carries operational value (routing, consent, expiry, polling). It would read better if the general purpose came first and the report_video specifics second, and the semicolon-chained lifetime sentence could be broken for scannability.

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?

With an output schema present, the description correctly focuses on input semantics, async polling, consent, and retention rather than return values, which covers what an agent needs before calling. The gaps are padding_seconds and the meaning/effect of title, neither documented in the description or schema.

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 only 22%, and the description compensates well for the highest-stakes fields: it explains the four kind branches, constrains evidence_ids to exact IDs from get_research_analysis, notes no selection is needed for report_video, and explains idempotency_key reuse. It leaves padding_seconds and title completely unexplained in both description and schema, so a couple of parameters still require guessing.

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 names the concrete outputs (retained MP4 with branded bookends and chapters, editable PowerPoint, individual audio clip, legacy reel ZIP) sourced from a completed/partial Hub run, which is clearly distinct from siblings like generate_report or queue_report_slides. It opens with the report_video variant rather than a one-line statement of the tool's overall job, so a reader must assemble the full purpose across sentences.

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?

It gives explicit routing rules: use report_video for Highlights with no evidence selection needed, presentations include all findings, audio requires an explicit export instruction, and evidence_ids must come from get_research_analysis highlights. It also names the follow-up path (poll get_research_deliverable or tasks/get for Tasks clients) and the timeout recovery (reuse the idempotency key).

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