Skip to main content
Glama

Swapwire

Check a quote, invoice or ad against a license

check_document
Read-onlyIdempotent

Check whether a contractor's quote, invoice, contract, business card, ad or truck photo matches a California license in this dataset. Send the document as text, as a PNG or JPEG image (base64), or both, plus the license number to check against (if the text shows a license number from the dataset, it is used). Returns a verdict (consistent, number_only, mismatch or unclear; number_only means only the license number matched, which anyone could copy), whether the business name and license number on the document match the record, whether the work described falls outside the license's classifications, and the license's status, bond and workers' comp checks. The verdict is a reading of the document, not proof. The document is read by TypeSafe's Jev model and is not stored by Swapwire; remove a homeowner's personal details before sending if you can.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "check_document"
  }
}

Input Schema

NameRequiredDescriptionDefault
textNoThe document's text, e.g. a pasted quote or ad. Up to 20,000 characters.
image_base64NoA photo or scan of the document, base64-encoded PNG or JPEG, up to 5 MB.
image_formatNoFormat of image_base64, if it can't be detected.
license_numberNoCSLB license number to check against, digits only. Optional if the text shows it.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint, but the description adds real value: the document is read by TypeSafe's Jev model, is not stored by Swapwire, and the verdict is 'a reading of the document, not proof' with the meaning of number_only spelled out. It does not characterize latency, rate limits, or failure/error behavior for unreadable images, which keeps it below a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core check, then the inputs, then the return value, then the privacy caveat — a sensible order with no filler. The verdict-definition clause is dense and reads as a run-on, costing it a point.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, so the description must carry the return contract, and it does: verdict values including the important number_only caveat, name/number match, classification overreach, and status, bond and workers' comp checks. For a document-analysis tool with a clear privacy caveat, nothing an agent needs before calling is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3, but the description adds the combination semantics the schema does not state: send text, image, or both, with the license number resolved from the text if present. That clarifies interaction between the inputs rather than repeating them.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Specific verb plus resource: 'Check whether a contractor's quote, invoice, contract, business card, ad or truck photo matches a California license in this dataset.' The document types and the license-matching target make it unmistakable against siblings like get_license or search_licenses, which take only a number or query.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description makes the trigger condition clear (you have a document and want to verify it against a license) and explains that license_number is optional when the text already shows one. It stops short of naming an alternative like get_license for pure number lookups, so there is no explicit when-not guidance.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources