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

Annotations already declare destructive, non-idempotent, non-open-world behavior; the description adds crucial context: human approval must happen first, the card must be named, every charge triggers an email, and specific failure modes route to topup_url. It does not explicitly warn about duplicate charges on retry despite the non-idempotent annotation, but overall it adds strong behavioral context.

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 purpose is front-loaded, then approval preconditions, fallback routing, and email notification follow in compact form. Every sentence carries operational information with no redundant restatement.

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 destructive financial mutation with no output schema, the description covers the approval workflow, fallback alternatives, and notification behavior well. It could more explicitly address retry/duplicate-charge risk or post-charge verification, but the core operational picture is complete enough to invoke correctly.

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%, covering amount bounds and the human_approved flag. The description adds meaningful semantics beyond the schema: the amount and card must have been named in the approval conversation, get_balance shows the card, and human_approved should be true only after an explicit yes.

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 specific verb and resource: 'Add credit by charging your human's saved card.' It distinguishes the tool from the sibling create_topup by explicitly routing cases with no saved card, disabled agent charges, or bank confirmation to the topup_url flow.

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 gives an explicit precondition: ask the human in this conversation, name the amount and card, get a yes, then set human_approved true. It also names three situations where the agent should not use this tool and should use create_topup instead.

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