Validate and stage a purchase batch of 1-10 cases, linking each receipt to draft bill lines with explicit approval, payment, and reconciliation steps without writing to Billy.
Preflight and save an ordered purchase batch (1-10 cases). Each case binds an original receipt, exact draft lines and explicit approval/payment/reconciliation stages. No Billy writes.
| Name | Required | Description | Default |
|---|---|---|---|
| cases | Yes | ||
| reason | Yes |
Changes observed during successful MCP inspections.
v0.2.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already provide readOnlyHint=false and destructiveHint=true. The description adds the key context that despite the batch being saved, no writes occur in Billy, and that each case passes through explicit approval/payment/reconciliation stages. This complements rather than contradicts the annotations.
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?
Two sentences with no filler; the core purpose is front-loaded and the behavioral caveat is in the second sentence. Every clause adds meaning.
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 tool with a deeply nested input schema, 0% schema descriptions, and no output schema, this overview is insufficient. The agent still lacks guidance on the `reason` field, the structure of `bill.lines`, payment optionality, and what the tool returns or does on preflight failure. It is a useful summary, not a complete spec.
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%, so the description carries the burden. It does map top-level concepts to parameters: cases, receipt, draft lines, approval/payment/reconciliation stages. However, it never mentions the `reason` parameter or explains the exact required fields (contactId, lines, etc.), leaving the agent to infer from the schema alone.
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 opens with 'Preflight and save an ordered purchase batch (1-10 cases),' a specific action on a specific resource. It also states 'No Billy writes,' which clearly separates this from execution tools. This is enough to distinguish it from siblings like billy_batch_execute or billy_prepare.
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 phrase 'No Billy writes' gives a clear exclusion: this tool is for preparation/saving only, not for committing to Billy. It implies use before execution tools, but it does not name alternatives or explicitly state when not to use it. Thus it provides clear context but no explicit routing.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.