Record manual payment

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

Annotations already declare readOnlyHint=false, idempotentHint=false, and destructiveHint=false. The description adds valuable context beyond that: it wraps Transactions.add then Transactions.apply, explicitly states no charge is performed, and explains the optional application behavior. This gives the agent a clear mental model of side effects without contradicting any annotation.

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?

Three sentences with no filler. The main purpose is front-loaded, followed by the key distinction (does not charge) and a critical parameter behavior. Every clause earns its place and the description is easy to parse quickly.

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 moderately complex 7-parameter tool with no output schema and annotations present, the description covers the essential behavior, the internal wrapper, and the optional application logic. It doesn't mention prerequisites (e.g., client must exist, currency validity) or what the response contains, but those are less critical for correct invocation and are partly implied by schema constraints.

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 only 57%, so the description needs to compensate for undocumented parameters. It adds meaningful semantics for apply_to (omission yields unapplied credit) and clarifies the overall purpose of amount and client_id through context. However, it doesn't explicitly detail client_id, amount, or currency beyond what the schema's types imply, leaving some ambiguity for those required fields.

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 uses a specific verb ('record') and resource ('offline payment'), names concrete examples (bank transfer, cash, check), and explicitly states what it does not do ('Does not charge anything'). It distinguishes itself from charging/payment tools like process_payment by emphasizing it only records already received money.

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?

The description clearly frames when to use this tool: for offline payments already received, not for charging. It also provides conditional guidance on apply_to ('Omit apply_to to leave the amount as unapplied credit'). It doesn't explicitly name sibling alternatives or when-not conditions, but the 'does not charge' clause implicitly differentiates it from charging tools.

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