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

Annotations declare readOnlyHint=true and destructiveHint=false, so the safe-read nature is already known. The description adds meaningful behavioral detail: the data is de-identified and never contains PII, payment is required before records are returned, failure returns a 402 with price and preview count, and there is a per-record price with a minimum per pull. It does not explicitly state pagination limits or rate limits, but the schema's maximum on limit covers the main cap. It adds material context beyond 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?

The description is compact for the amount of information it carries: one dense sentence listing the dataset contents and exclusions, then short actionable sentences for filters, pricing, payment, and the sample endpoint. It front-loads the dataset identity and PII exclusions before the mechanics. It is slightly list-heavy, but every clause earns its place.

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 data-pull tool with 11 parameters, no output schema, and only 36% schema coverage, this description covers the important gaps: what the data is, what it excludes, how to filter, how to pay, what failure looks like, and where to find the schema and sample. It doesn't describe the exact response format beyond the preview count, but the pointer to /data.json mitigates that. It is strong given the available structured metadata.

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 only 36%, so the description must clarify parameters that the schema leaves bare. It does: it explains door and vendor as the 'door' and 'AI vendor that asked,' and states the filters (state, since, until) and pagination (limit, offset). It also explains payment parameters (buyer_key, x402 payment, MPP credential, AP2 mandate) at a conceptual level. It doesn't give exact formats for the date-time strings or the payment payload, but it goes well beyond the sparse 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?

The title states exactly what the tool provides ('Buy de-identified demand records') and the description gives a specific inventory of the dataset plus what is excluded. It is clearly distinct from siblings like get_quotes or pull_requests because it names the resource (de-identified demand dataset) and the sales/purchase action explicitly.

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?

The description explicitly lists the filter dimensions (state, since, until, door, vendor), the pagination controls (limit, offset), and the payment paths (prepaid buyer key, x402, MPP, AP2). It also tells the agent what happens without payment (402 with price and preview count), which is a strong when-to-use and how-to-use signal. It doesn't name a sibling alternative, but the resource is so specific and the payment guidance is so actionable that an agent can select it confidently.

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