prepare_interim_split

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

The description says 'prepare' which implies creating a mutable prepared action, but the annotations declare readOnlyHint=true. This contradicts the read-only behavior. The description does add 'but do not execute' which is helpful, but the contradiction with the annotation is a serious issue.

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 a single, well-structured sentence that front-loads the primary actions. It is concise and contains no fluff, every word adds value.

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 description is too short given the tool's complexity. It does not explain what 'prepare' actually does, whether it creates a draft, how it interacts with cancel/execute sibling tools, or what the output looks like. With no output schema and minimal annotations, this leaves significant gaps.

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 description coverage is 0% and the description provides no explanation of client_id, target_month, target_year, or invoice_key. With four parameters and no parameter-level descriptions, the agent has to guess how to populate them.

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 tool validates live FYI interims and prepares a permanent full-invoice service split without executing it. The verb 'prepare' and resource 'service split' are specific, and the contrast with 'do not execute' distinguishes it from execution 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 gives clear context: it is for validating interims and preparing a permanent split. It does not name explicit alternatives, but the context is sufficient for an agent to recognize when to use this tool, especially with sibling tools like prepare_direct_invoice and prepare_job_allocation.

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