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

Annotations only mark this as a non-readonly, non-destructive, non-idempotent write; the description adds the economically important context: pricing (0.01 USDC/query), a per-session cap (max 20 queries/session for this listing), and that the session is prepaid and must be funded before querying. It doesn't disclose balance requirements, failure modes on insufficient funds, or session expiry.

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 compact sentences, front-loaded with the value proposition and followed by cost and next steps. The inline per-listing example ('statwatch: STAT News pharma & biotech industry press …') with nested parentheses is noise that will not generalize and will go stale.

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 stateful, money-moving tool with no output schema and 0 required parameters, the description covers the workflow and price but not what a successful open returns (session id, escrow, expiry) or what the agent should do with it. An agent can invoke it, but completing the full lifecycle requires inference from sibling tools.

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%, and the description only adds meaning for max_queries (by noting the listing's 20-query cap, versus the schema's generic maximum of 50). It says nothing about open_tx_hash or proof_escrow_id, and doesn't clarify listing_slug vs listing_id or the buyer_address default beyond what the schema already documents. Baseline 3 is right.

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 uses a concrete verb and resource ('Buy per-query access', 'Open a prepaid session') and distinguishes free exploration from paid access. The closing sequence ('then fund and query') implicitly separates this step from data_session_fund and data_session_query, though it doesn't name those siblings 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?

It gives a clear conditional: first taste is free via data_preview, paid access requires opening a session. It also states the follow-up sequence (open, then fund, then query). It stops short of addressing alternatives such as data_session_funding_package or data_session_attach_escrow, or when a session is not needed at all.

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