Read the spend ledger

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

Annotations already declare read-only and idempotent behavior. The description adds value by specifying the content (prompt, costs, verdict, files) and noting it's an append-only log, which helps the agent understand the tool's nature without contradicting 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?

Two sentences efficiently convey the tool's purpose and key details. The first sentence is dense with specific information, and the second adds context. No redundant or vague phrasing.

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 explains what the tool returns but omits details like pagination, ordering, or how to interpret the data. With no output schema, more context about the response structure would improve completeness.

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 50%, with only response_format having a description. The tool description does not mention or clarify parameters. The schema itself provides good constraints for limit and response_format, so baseline is acceptable but no extra value from 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?

The description clearly states the tool returns an append-only log of generation attempts with specific fields like prompt, cost, and verdict. It identifies the resource and action, though it does not explicitly distinguish from sibling tools.

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?

No guidance on when to use this tool versus alternatives like flow_budget or flow_estimate_cost. The description implies it's for auditing spend, but lacks explicit usage context or exclusions.

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