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

Annotations already declare readOnlyHint and idempotentHint, so the safety profile is covered. The description adds valuable behavioral context beyond annotations: required auth mechanism, guest-call restrictions, HTTP method, and the exact nature of the returned data (funding instructions and createEscrow calldata, not an actual escrow execution). No contradiction with annotations found.

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-loaded with the core purpose, followed by authentication, output, and call constraints. Every sentence adds useful information. The opening 'Buy per-query access' is a bit promotional rather than strictly functional, preventing a perfect score.

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?

Given the tool's complexity, the description covers prerequisites, return value, endpoint, auth, and guest eligibility. It does not explicitly explain how this relates to data_session_fund or attach_escrow, but the essential calling context is present.

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?

The input schema already fully documents session_id as the UUID of an opened data session; schema coverage is 100%. The description does not add significant parameter-level detail beyond restating that the session must be opened, so the baseline score of 3 is appropriate.

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 identifies the tool's resource (funding package for a data session) and output (funding instructions and createEscrow calldata). The phrase 'Buy per-query access' is slightly misleading because the tool actually returns funding instructions rather than executing a purchase, but the subsequent sentences clarify the real behavior.

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 states prerequisites: requires an agent API key, must target an already-opened data session, and is not guest-callable. It also mentions data_preview as a free alternative, providing useful when-to-use context. It does not explicitly contrast with sibling tools like data_session_fund, but the context is clear enough.

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