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

Annotations already establish read-only, idempotent, non-destructive; the description goes well beyond that with pricing mechanics the annotations cannot carry — per-row rate ($0.005 open-data rows), $0.01 per-call fee, rounding once to the nearest cent, floor of $0.02 and cap at the whole list price, plus bundle substitution messaging.

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?

Purpose is front-loaded, but the body is a dense paragraph of billing rules for a single-parameter tool, with the count_locations pricing point made twice ('count_locations with filters gives the exact price of the rows' and again with 'same filters, limit and offset'). Several sentences could be compressed without losing routing or pricing 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?

No output schema exists, so the description must describe returns, which it does: line items, total, how each list is sold, per-call fee, and price.breakdown. It is largely sufficient for an agent to interpret results, though the exact response shape (field names beyond price.breakdown) is left implicit.

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?

With one parameter at 100% schema coverage the baseline is 3, but the description adds real semantic meaning to the slug values themselves: slugs beginning with overture- are row-only lists, and list size determines whether a whole-file price exists at all. It does not document the 1–50 item bounds, which the schema handles.

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?

Opens with a specific verb and resource: 'Line-item prices and total for a list of dataset slugs,' plus the scope 'each with how it is sold'. It explicitly separates itself from siblings by naming create_checkout, buy_dataset, query_locations and create_query_checkout as the tools enforcing the same rule, so an agent can place it in the workflow without opening another 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 strong conditional routing: row-only (overture-) lists have no file to buy, our own lists under 5,000 records are sold whole only, and count_locations with the same filters/limit/offset quotes that exact page before payment. It stops short of a plain directive ('call this before create_checkout to preview cost'), so the when-to-use is inferred from the surrounding rules rather than stated.

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