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

Annotations already declare the safety profile (not read-only, not destructive, not idempotent), so the description's job is to add economics and lifecycle context — and it does: 0.01 USDC/query, a per-session query cap, and the fact that opening is only the first of a fund-then-query sequence. It stops short of saying that each call mints a new session (consistent with idempotentHint=false) or what credentials the session yields.

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 workflow statement is front-loaded and useful, but the listing example is hard-coded to one specific listing with awkwardly nested parentheses ("0.01 USDC/query (max 20 queries/session)))") that muddle the pricing and cap. Three sentences where two tight ones would suffice.

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 non-idempotent state-creating tool with six optional parameters and no output schema, the description covers cost and the fund/query pipeline but omits what the call returns (session handle / escrow id), whether payment happens at open or at fund, and any authorization expectations. Adequate but with real gaps.

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 50%: listing_id, listing_slug, and buyer_address carry descriptions (including the slug-from-benchmarks_get/data_directory_get hint and the default-wallet behavior), but max_queries, open_tx_hash, and proof_escrow_id are undocumented. The description adds only the pricing/cap figure tied loosely to max_queries, so baseline 3 is appropriate.

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 states a specific action on a specific resource: open a prepaid per-query data session for a named listing, then fund and query it. It also names an adjacent sibling (data_preview) as the free alternative, so an agent can place it in the family. The opening phrase "Buy per-query access" is slightly marketing-flavored rather than naming the crate/session object directly, which keeps it short of a 5.

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 explicitly routes the free-preview case to data_preview and lays out the sequence "Open a prepaid session, then fund and query," naming the follow-on tools' purpose. What's missing is any exclusion or prerequisite detail (e.g. that an unfunded session cannot yet query, or when to prefer listing_slug vs listing_id).

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