Skip to main content
Glama

Add expense receipt

add_expense_receipt

Attach a receipt image to an expense. Send the image as base64 with a filename or content_type, or as a data URL. PNG, JPEG, WebP, GIF, and HEIC images are accepted. PDF receipts are not.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "expense_id": "<expense_id>"
    },
    "name": "add_expense_receipt"
  }
}

Input Schema

NameRequiredDescriptionDefault
dataNoAlias for image_base64.
filenameNoThe receipt file name. Used to infer content_type when it is omitted.
expense_idYes
business_idNoThe id of the business to act on, from list_businesses. Optional when this connection covers a single business.
content_typeNoThe receipt image MIME type, such as image/jpeg.
image_base64NoBase64-encoded receipt image (PNG, JPEG, WebP, GIF, or HEIC).
receipt_data_urlNoA data URL for the receipt image, if the image is not sent as base64.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false and destructiveHint=false, so the bar is lower; the description still adds valuable behavior: accepted formats (PNG, JPEG, WebP, GIF, HEIC) and an explicit rejection rule (no PDF). It does not say what happens if a receipt already exists or whether an attachment is replaced or appended, but the format contract is concrete and useful.

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

Conciseness5/5

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

Three short sentences, front-loaded with the action, then delivery formats, then the one hard exclusion. Nothing is repeated from the title and no sentence is filler.

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

Completeness4/5

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

For a single-purpose attachment tool with no output schema, this covers the crucial format contract and the PDF exclusion. Minor gaps remain around duplicates/replacement behavior and any size limit, which an agent might reasonably want before sending a large payload.

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 coverage is high (86%), giving a baseline of 3, and the description still clarifies the mutual-alternative relationship among the input shapes: base64 plus filename/content_type, or a data URL. That meaningfully disambiguates the overlapping data/image_base64/receipt_data_url properties beyond their individual schema text.

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?

States a specific verb and resource: "Attach a receipt image to an expense." The action is distinct from create_expense/get_expense/update_expense siblings, so an agent can select it without opening a schema.

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

Usage Guidelines3/5

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

Gives clear in-context constraints (must supply base64 with filename/content_type, or a data URL; PDFs rejected), which steers format choice. However, it offers no guidance on when to use this versus create_expense or update_expense, or prerequisites such as an existing expense_id.

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