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

Annotations only declare the mutation/safety profile (readOnlyHint=false, openWorldHint=true, destructiveHint=false); the description supplies the operationally important extras those annotations cannot: per-unit pricing (9 credits per creator plus 20 per video, capped at 4,090), the 60 s wait before falling back to a run id, and that the Digest is a single ranked result set. It does not say whether a partial failure still charges credits or what happens when `max_credits` is breached, which is the main remaining gap for a paid, non-read-only tool.

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 the use case, then exclusions, then cost, then limits and async behavior — a sensible priority order with no filler sentences. The telegraphic fragments ('Not for a niche or topic: use research', 'estimate=true quotes') are efficient but border on clipped, which costs a point.

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?

For a paid, open-world, potentially long-running tool this covers everything an agent needs before calling: scope, exclusions, cost, caps, timeouts, run-id fallback, quoting mode, and free re-read. An output schema exists, so return-value detail is correctly left out.

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 71% and the description fills several gaps: default 25 videos per creator (max 50, 200 in all) against `videos_per_creator`, the 10-creator cap against `creators`, and the price ceiling that gives `max_credits` meaning. It never explains `max_credits`'s breach behavior or how `collection_id` combines with `creators`, leaving one parameter semantically thin.

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 concrete verb chain and output: reads recent videos, analyses all, scores each against its own Creator's median, returns one Digest with ranked ids. It also names the resource boundary (Creators given as handles, profile URLs or a Collection) and contrasts with `research` and `get_creator`, so an agent can distinguish it from siblings without reading any 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?

Opens with the triggering condition ('Use when the Customer names Creators... asking what works for them') and then gives two explicit exclusions with the sibling to use instead: niche/topic goes to `research`, single-Creator profile goes to `get_creator`. It also routes the follow-up ('Re-read with get_research (free)') and the async fallback ('returns a run id for get_run').

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