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

The description discloses meaningful behavioral traits not present in the annotations: each query costs 0.01 USDC, there is a maximum of 20 queries per session, and access is prepaid. It also implies consumption of session funds. It does not mention failure/refund behavior or whether failed queries still count against the quota, but the cost and quota disclosure go well beyond the sparse 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?

The description is compact and front-loads the core action, then adds pricing and the required sequence. The specific listing example adds useful context but also some noise; still, every sentence contributes operational or commercial guidance.

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 the core happy path, the description is reasonably complete: it gives the sequence, price, quota, and free-preview alternative. However, with five parameters and no output schema, it omits return-value expectations and the purpose of delivery_receipt and sandbox_receipt. An agent can likely perform the basic query but may struggle with optional receipt-related advanced usage.

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%, so the description should compensate by explaining parameters. It does not explain k, query, delivery_receipt, or sandbox_receipt. The session_id is explained in the schema, and the cost/quota context hints at the paid nature of query, but several parameters remain semantically underdescribed.

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 the tool as the final step in a prepaid data-session flow: data_session_open → data_session_fund → data_session_query, and the input schema adds 'Run a prepaid query against a funded data session.' It distinguishes itself from data_preview and data_session_fund via the sequence and 'first taste free via data_preview.' Minor ambiguity remains because 'Buy per-query access' could be read as the funding step rather than the query execution step.

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 gives explicit workflow guidance: open a session, fund it, then query. It also points users to data_preview for a free first taste, which helps an agent decide between the preview and paid query path. It does not spell out explicit 'do not use when...' conditions, but the sequence makes the intended usage clear.

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