propose_split

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It explicitly states 'Read-only' which is crucial safety information, and explains the scaling behavior and the prerequisite that all lines must be categorized before applying the split. This adds useful context beyond the tool name.

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 only three sentences, with the core purpose stated first. Every sentence adds value—purpose, read-only safety, and the required workflow—without redundancy or fluff.

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 has a single parameter and no output schema, so the description must cover both purpose and usage. It does so by explaining the read-only nature, the scaling, and the next step (apply_split). Minor gaps include no mention of return format or error cases, but for a simple tool this is mostly complete.

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 input schema has one parameter, txn_id, with zero description coverage. The description does not mention txn_id or explain how to identify the Amazon charge, leaving parameter semantics entirely to inference. Though the phrase 'behind an Amazon charge' vaguely implies the transaction ID, it is not explicit enough, so the description fails to compensate for the 0% schema coverage.

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 clearly states that the tool returns item lines behind an Amazon charge, scaled to the actual charged amount. It also distinguishes itself from apply_split by instructing to call that only after categorizing, giving it a distinct role among the many sibling tools.

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 provides an explicit workflow: assign a category to every line, show the user, and only then call apply_split. This tells the agent exactly when to use this tool and names the next tool to use, which is strong guidance compared to alternatives.

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