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

Annotations only carry false hints, so the description must carry behavioral weight. It does by disclosing that calls are paid/prepaid, require an API key, return a purchase receipt, and can optionally sign a DeliveryReceipt via sandbox_receipt. It does not discuss idempotency or failure modes, but the billing and auth disclosures exceed what annotations provide.

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?

Four tight sentences front-load the core value and then layer auth, sandbox behavior, and endpoint. There is no filler or repetition of schema details.

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?

The description covers the high-level flow, auth, and sandbox path, but with five parameters, no output schema, and low schema coverage, the undocumented delivery_receipt and k semantics leave a real gap. It is serviceable for a basic query but not fully complete for a paid-query tool with these optional parameters.

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 only 40% (session_id and sandbox_receipt have descriptions; query, k, and delivery_receipt do not). The description adds no meaning for the undocumented parameters—'k' remains an unexplained integer and delivery_receipt is never mentioned—so the agent must guess at two significant inputs.

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 description opens with a concrete action—'Buy per-query access to live data listings'—and specifies the operation ('Run a prepaid query against a funded data session'), the return value ('attested hits plus a purchase receipt'), and the REST endpoint. This clearly separates it from siblings like data_session_open and data_session_fund, which prepare sessions, and from data_preview, which is the free alternative.

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?

It states prerequisites (agent API key, funded data session, not guest-callable), directs the agent to data_preview for a free first taste, and gives the exact HTTP verb and path. It does not explicitly enumerate when not to use this tool, but the context is strong enough to route an agent to the right sibling.

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