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

While the description states the query is 'prepaid' and 'against a funded data session', it does not explicitly mention side effects such as deducting from the session balance or consuming credits. Annotations indicate readOnlyHint=false and idempotentHint=false, but the description could be more transparent about the cost implications.

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 somewhat verbose, including marketing-like phrases ('first taste free via data_preview') and specific pricing details (0.01 USDC per query) that are not essential for invoking the tool. It could be tightened to focus on the action and prerequisites. However, it is not excessively long and the key information 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 lacks details about the output format, response structure, or potential errors. Given that this is a query tool, an agent would need to know what the returned data looks like (e.g., fields, pagination, status codes) to use the results effectively. The absence of an output schema makes this gap more significant.

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?

Only two of the five parameters (session_id and sandbox_receipt) have descriptions. The schema description is generic and does not explain k, query, or delivery_receipt. The description text mentions 'REST body + session id' but does not elaborate on the individual parameters, leaving agents guessing about their roles.

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 clearly states the tool's purpose: running a prepaid query against a funded data session. It distinguishes this from related tools like data_session_open and data_session_fund by describing the query action and referencing the session lifecycle.

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 mentions the sequence data_session_open → data_session_fund → data_session_query, indicating when this tool should be used after funding. It also contrasts with data_preview as a free trial, giving clear guidance on which tool to choose for different stages.

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