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

Annotations already declare non-read-only, non-idempotent, non-destructive, closed-world, so the bar is lower. The description adds genuinely useful economics the annotations do not carry: prepaid session model, 0.01 USDC per query, and a max-20-queries-per-session cap. It omits failure/refund behavior and what an opened session returns, so not a 5.

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?

Three sentences, front-loaded with the purchase action, followed by the free alternative and the flow. The listing example with stacked parentheses ("0.01 USDC/query (max 20 queries/session))") is dense and looks like injected example data that may go stale, which costs a point.

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 money-spending mutation tool with no output schema, the description never says what comes back (presumably a session handle needed by data_session_query/fund) nor how the open_tx_hash / proof_escrow_id escrow path differs from the plain path. The pricing and ordering context is solid, but an agent could call this and not know what to do with the result.

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 are described in-schema, and the description adds the per-session query cap that gives context for max_queries. However open_tx_hash and proof_escrow_id have no description in either place, and for a payment-bearing tool those are the two parameters an agent most needs explained. Baseline 3.

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 concrete verb and resource ("Buy per-query access to live data listings") and positions the call in a sequence: free preview via data_preview, then open a prepaid session, then fund and query. That sequence distinguishes it from data_preview, data_session_fund and data_session_query. The embedded "Listing: samsungwatch..." example is concrete but reads as if it were the only available listing, which slightly muddies the generic purpose.

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?

"first taste free via data_preview" explicitly names the alternative and the condition under which it should be preferred, and "Open a prepaid session, then fund and query" gives the ordering constraint relative to the fund/query siblings. No explicit when-not guidance (e.g. when to use the escrow path instead via data_session_attach_escrow), so it stops short of a 5.

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