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

The description adds behavioral context beyond annotations by disclosing per-query cost (0.01 USDC) and a session limit (max 20 queries/session), and by implying the query consumes prepaid balance ('Buy per-query access'). Annotations are all false and provide no safety or side-effect information, so the description carries the burden, but it omits critical details like authorization requirements, failure behavior, or effects on session state. It is partially transparent but not comprehensive.

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 three sentences and not excessively long, but it leads with pricing and a specific listing ('Quanta Magazine — Deep Science, Math & Physics Journalism') that is peripheral to invoking the tool. The sequence is useful but placed at the end. It is adequately concise but not optimally structured; some content could be trimmed or the actual purpose front-loaded.

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?

With 5 parameters, no output schema, and uninformative annotations, the description should provide more operational context. It explains the prerequisite sequence and pricing but does not explain how to form a query, what k and delivery_receipt control, what a successful response looks like, or what errors may occur. An agent cannot fully infer how to invoke this tool correctly from the description alone.

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 40% (descriptions for session_id and sandbox_receipt only), leaving query, k, and delivery_receipt undocumented in the schema. The tool description does not compensate: it never mentions any parameter by name or explains what query, k, or delivery_receipt mean. It only generically references 'per-query access,' which does not clarify the parameters. This is a significant gap for an agent trying to fill the query field or understand the optional k and delivery_receipt.

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 'Buy per-query access to live data listings,' which frames this as a purchase action rather than a query execution. The actual verb is never stated; the tool name and the trailing sequence 'data_session_open → data_session_fund → data_session_query' imply it queries a funded session, but the description itself does not clearly say 'query' or 'run a query.' This is misleading and vague, closer to a tautology of the name than a specific functional statement.

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 names data_preview as the free alternative ('first taste free via data_preview') and provides a call sequence 'data_session_open → data_session_fund → data_session_query.' This tells an agent when to use this tool (after funding) and when to use the free preview instead. It does not state exclusions, but the sequence and alternative give clear contextual guidance.

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