apply_split

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

Without annotations, the description carries the burden. It discloses the validation behavior (write refused if lines don't sum) and warns about the consequence of wrong allocations ('silently misstates a budget'). However, it omits other behavioral traits like idempotency, permission requirements, or what happens to existing splits, so transparency is partial.

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 three concise sentences that are front-loaded with the purpose. Every sentence adds value: the purpose, the critical constraint, and the user confirmation requirement. No wasted words.

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?

Despite its clarity, the description is incomplete for a mutation tool with no annotations and no output schema. It doesn't explain what a successful response looks like, how lines are structured, whether the split replaces existing data, or what 'source' is. These gaps make it inadequate for fully autonomous invocation.

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 0%, so the description must add meaning. It clarifies that 'lines' are category allocations and must sum to the charge, and implies 'txn_id' identifies the charge. However, it does not describe the internal structure of each line object or the optional 'source' parameter, leaving critical information undocumented.

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 the verb and resource: 'Split one charge across categories.' This identifies the action and target. It is distinct from sibling tools like set_txn_category or propose_split, though it doesn't explicitly name alternatives, so it doesn't perfectly differentiate from every sibling.

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 important usage constraints: 'Lines MUST sum to the charge exactly or the write is refused' and 'Confirm with the user first.' However, it does not specify when to use this tool over others (e.g., propose_split for planning), so the guidance is implied rather than explicit.

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