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

Annotations only cover readOnlyHint=false and openWorldHint=true; the description carries the rest: per-minute pricing tiers, a 1-minute per-video minimum, the free case for duplicates, the write-scope API-key requirement, and the asynchronous job lifecycle with its terminal statuses. This is far more behavioral context than the annotations supply.

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?

Dense and mostly front-loaded, with the action stated first, but it opens with a fragment ('Charged like `transcribe`.') and repeats the pricing point twice ('$0.10/min ... by default' and 'Prices are the service defaults'). Eight sentences for one tool is on the heavy side, though nearly all carry real information.

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 no output schema, the description still supplies what an agent needs to interpret results: the status vocabulary, the meaning of `completed` (transcribed and indexed, collection queryable), and the polling cadence. Auth, pricing, idempotency, and dedup behavior are all covered, so nothing material 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%, so the baseline is 3, but the description adds pricing meaning to parameters the schema only labels: quality drives $0.10/min vs $0.25/min, and quote_id locks an exact quoted price. It leaves max_videos_per_channel and the channel_url/url split entirely to the schema.

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 ('start an ingest job in an existing collection' for the given YouTube URLs), names the exact endpoint POST /v1/collections/{collectionId}/sources, and uses 'Expand' to signal that channels/playlists are flattened into individual videos. An agent knows precisely what happens as a result of calling it.

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 concrete operational guidance: pass a quote_id from `quote` to lock the price, poll `get_status` every 10-30s until completed/partial/failed, and notes that videos already in the collection are free. It references two siblings (quote, transcribe) but never explicitly routes the agent between this tool and its near-identical sibling add_source (singular), which is the most likely selection mistake.

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