Audit Credit Card Payments

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

Even though annotations already mark the tool read-only, idempotent, and non-destructive, the description adds valuable behavior: it 'makes no changes,' reports each card's balance/category balance/difference/status, and warns that pending/uncleared transactions can cause transient sub-dollar differences to be treated as timing rather than error. This goes beyond the 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 front-loaded with the core audit purpose and flows naturally into purpose, healthy/unhealthy interpretation, output contents, non-mutating behavior, and a practical caveat. Every sentence adds information; there is no filler or repetition.

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 a read-only audit tool with an output schema and a single optional parameter, the description fully covers what the tool computes, what the results mean, what it does not do, and how to interpret edge cases. Nothing material is missing for an agent to invoke it confidently.

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 only parameter, budgetId, is fully described in the schema ('Budget ID (uses default if not provided)'), so schema coverage is 100%. The description adds no budgetId-specific semantics, but none are needed because the schema already handles it; this is the appropriate baseline score.

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 opens with 'Read-only audit of credit card payment categories' and precisely defines the behavior: comparing each open card/line-of-credit balance with the corresponding payment category's available balance. This clearly distinguishes it from generic read tools like get_account or get_category, and from the fix-oriented update_month_category tool.

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?

It explicitly states when this audit is relevant (healthy budgets show a sign-flipped match; shortfalls indicate underfunded future payments) and gives an actionable alternative: 'fix shortfalls by assigning to the payment category via update_month_category.' This is strong when-to-use and when-not-to-use guidance.

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