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

Annotations only declare readOnlyHint=true and openWorldHint=false; the description goes well beyond that by disclosing byte-budgeted chunking, the `complete`/`next_cursor` continuation contract, the attribution + rubric-citation obligation, and concrete pricing ($0.002/row, $0.50 minimum, plan inclusions). These are exactly the operational facts an agent needs and none of them are in the annotations.

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 but mostly earned — each clause covers dataset contents, paging, licensing or pricing. The main flaw is front-loading: the first five words are a licence/plan parenthetical rather than the core action, and the per-dataset payload detail is long enough to be skimmed. Still, no sentence is pure filler.

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 and no required parameters, the description carries the return-shape burden itself and does so — chunked `data`, `complete`, `next_cursor` — plus attribution and cost so the agent can decide whether a bulk licence call is appropriate. Nothing needed to invoke it correctly 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 description coverage is 100%, so the baseline is 3, but the description adds substantive meaning: it expands each `dataset` enum value with the actual payload contents (facets/trend/rubric+provenance; parallel date/composite/agent_readiness arrays; movement summary) and restates the cursor continuation rule as part of the paging loop. Only `co_brand` and `context` get no added explanation.

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 (export) and resource (dataset), then enumerates the three exports (`ratings`, `providers`, `history`) and what each contains. It also draws an explicit boundary against the paged search siblings — 'the WHOLE dataset, not a 100-row page' — so an agent can tell it apart from find_ratings without opening a 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?

Gives a clear audience/condition ('for media outlets and analysts licensing the data to publish rankings and trends') and singles out `history` as the one that cannot be reconstructed after the fact, which is a real selection signal. It never names the alternative tool (e.g. find_ratings, export_stack) or states when NOT to use it, so it stops short of full when/when-not routing.

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