Free. Validate an invoice JSON (the body for POST /v1/invoice.pdf, or the output of invoice_from_timesheet) and return computed subtotal, discount, tax and total, or a list of field errors. Same checks as the paid PDF route. Offline, no payment.
| Name | Required | Description | Default |
|---|---|---|---|
| invoice | Yes | Invoice object: from, to, number, issue_date, currency, line_items[{description, quantity, unit_price}], optional tax and discount |
Changes observed during successful MCP inspections.
Input schema / properties / invoice / descriptionAdded value: +"Invoice object: from, to, number, issue_date, currency, line_items[{description, quantity, unit_price}], optional tax and discount"Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly/idempotent/non-destructive/openWorld=false, but the description adds real value: it is free, offline, requires no payment, and performs the identical checks as the paid PDF route. It also discloses the two possible return shapes (computed totals vs. field errors), which is more than the annotations convey.
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 compact sentences, front-loaded with 'Free.' and immediately stating the action, input source, and outcomes. No filler or redundancy.
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 single-parameter validator with nested input, no output schema, and full annotation coverage, the description supplies everything needed: the input origin, the two return cases, and the offline/no-payment behavior. Nothing essential is missing.
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 100%, so the baseline is 3, but the description goes beyond it by explaining where the invoice object comes from (body for POST /v1/invoice.pdf, or output of invoice_from_timesheet), which tells the agent the required level of well-formedness. It adds meaningful context without restating the field list.
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?
States a specific verb (validate) and resource (an invoice JSON), and clarifies which shape of input it accepts — the body for POST /v1/invoice.pdf or the output of invoice_from_timesheet. This lets an agent distinguish it from the generation siblings without opening any schema.
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?
It makes the when clear: use this to run the same checks as the paid PDF route before committing, offline and free. It does not explicitly name alternatives to avoid (e.g. that this returns errors rather than generating a PDF), but the comparison to the paid route implies the intended pre-flight role.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.