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

The description discloses behavioral traits beyond the readOnlyHint=true annotation: it returns 'the Canadian mechanics and the retention rules,' and it 'computes the exact utilization before and after, the limit leaving the denominator, and whether it crosses a band upward' when supplied with cards/cardName. This richer context — what the tool actually produces — is genuinely additive and consistent with 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 longer than average, but dense with decision-relevant information: core purpose, when to call with no args, the ordering directive, and the conditional computation behavior. It is front-loaded with purpose and keeps the param-behavior detail for later. Every sentence earns its place for a tool with conditional behavior, so the length is justified rather than padded.

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 tool is complex — three optional parameters, conditional behavior, and a 25-item nested cards array — but an output schema exists so return values need no explanation. The description covers purpose, usage triggers, parameter-conditional behavior, and even the fallback logic (UTC vs local timezone in the today param). Nothing an agent needs to call it correctly is missing.

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 baseline is 3. The description adds value by explaining the conditional semantics of the parameters: calling with no arguments returns mechanics/rules, while supplying cards and cardName triggers utilization computation. The schema covers the parameter formats and meanings well, so the description only adds the conditional-behavior layer, which justifies a 4.

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 states a precise purpose with concrete examples ('should I cancel the credit card I never use', 'is it bad to close a card') covering cancelling, downgrading, and consolidating. It names the subject (Canadian card closure) and, by framing questions around closure, implicitly distinguishes it from related siblings like payoff_timeline and credit_plan without being a tautology.

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 when-to-call guidance is present: 'CALL THIS WITH NO ARGUMENTS when the person has not given card numbers' and a strong directive to 'call this first, then ask for what is missing' rather than answering from general knowledge. It even tells the agent the order of operations, which removes all ambiguity about when this tool is the right choice among 15 siblings.

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