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

Annotations declare a non-read-only, non-destructive, non-idempotent write, and the description adds real context: values are kept as printed, and later changes require a stated reason. It does not say what happens if facts already exist without a reason, nor what a repeat call does despite idempotentHint=false, leaving a modest gap.

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?

Front-loaded with the field list and the import-vs-correct decision, then the sourcing caveat. The trailing 'Effects: card statement facts recorded' is boilerplate that restates the opening, but the rest is tight.

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?

With no output schema and a mutation annotation set, the description covers what is recorded, when to use it versus the import path, and the correction precondition. What is missing is behavior on conflicting existing facts and whether the call replaces or merges recorded values.

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 coverage is 100%, so the baseline is 3; the description earns above that by adding sourcing rules the schema cannot express — copy figures as printed and never derive a minimum from the balance — and by tying the 'reason' parameter to correction scenarios.

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?

Specific verb ('Record') plus a precisely enumerated resource: minimum payment, payment due date, credit limit, purchase rate. It also scopes the tool as 'besides its rows,' which separates it from row-level statement import, and names purch_import_statement as the related sibling.

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?

Explicit routing: pass the fields with purch_import_statement when importing a statement, and use this tool only for a statement imported without them or to correct a misread. The when-to-use, the when-not-to-use, and the alternative are all stated.

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