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

Annotations are sparse (readOnlyHint=false, idempotentHint=false, destructiveHint=false), so the description carries the burden of explaining the paid, consumptive nature of the call. It discloses the 0.01 USDC cost per query, the 20-query session cap, and the specific data listing. It does not cover what happens on failed queries or how results are returned, but the key consumption behavior is transparent and consistent with the annotations.

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 short sentences, each earning its place: the paid-access model, the listing/price/quota, and the required session sequence. Information is front-loaded and no filler is present.

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?

The description is strong on selection and sequencing: which listing, what it costs, what to open/fund first, and the free preview route. But without an output schema and with 5 parameters only 40% covered, the missing semantics for k and delivery_receipt, plus unspecified query syntax, leave an agent with gaps for a fully confident call. It is adequate for a basic required-parameter invocation, not complete.

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 40%, so the description needs to compensate for undocumented parameters, but it does not explain k, delivery_receipt, or the expected query format. The only parameter-related context is that the query targets the fdarecall FDA recall listing and that queries are paid/limited. This leaves the central 'query' parameter and the optional k/receipt parameters under-specified for correct invocation.

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 identifies a specific resource (the fdarecall FDA recall listing) and the commercial transaction (per-query paid access), and the sequence line makes clear this tool executes the query step. It is distinguishashable from data_preview, data_session_open, and data_session_fund. However, the core action 'run a query' is stated more in the sequence/schema than in the description's own verb.

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 an explicit prerequisite sequence: data_session_open -> data_session_fund -> data_session_query, and mentions data_preview as the free first-taste alternative. This tells an agent when to use this tool and what must happen before calling it. No comparable guidance is needed beyond that.

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