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

Annotations cover the safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false), and the description adds material context beyond them: cost per query (0.01 USDC), a per-session cap (max 20 queries), and that the operation is prepaid against a funded session. It omits failure/refund behavior and receipt handling, but the cost and rate-limit disclosures are exactly the kind of added value the annotations do not carry.

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 dense sentences with the cost and free-alternative front-loaded, then the listing detail, then the prerequisite chain. The hard-coded 'nvidiawatch' listing line is arguably inventory-specific rather than tool-specific, but it does convey price/scope efficiently.

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 5-parameter, non-idempotent, money-spending tool with no output schema, the description covers cost, cap, and prerequisites but leaves the two undocumented parameters (k, query) and the return shape entirely unaddressed. Adequate for the workflow, incomplete for correct invocation.

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%: 'k' and 'query' have no schema descriptions at all, and the description never explains them — it does not say what 'k' controls (result count?) or what query syntax is expected. 'delivery_receipt' is also unexplained. Only session_id and sandbox_receipt are documented, and that documentation lives in the schema, not the description.

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 specific action ('Buy per-query access to live data listings') with the pricing model and the exact chain that leads here, so the agent knows this is the paid execution step of a session flow. It stops short of naming the sibling tools it replaces for the free case, but the resource and verb are unambiguous.

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?

Explicitly routes the agent: 'first taste free via data_preview' for a no-cost alternative, and 'Sequence: data_session_open → data_session_fund → data_session_query' for the prerequisites. It does not state when this tool should NOT be used (e.g. once the 20-query cap is hit or the session is unfunded), so it falls just 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.