Skip to main content
Glama

upload_accounting_document

Upload a company's BALANCE SHEET, P&L or VAT return (PDF, PNG, JPEG, XLSX) to be read; queued, follow get_accounting_document. fiscal_year when the file does not say; force re-reads a file already read. file_base64 is the file's raw bytes, base64.

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": {
      "company_id": "<company_id>",
      "filename": "<filename>",
      "file_base64": "<file_base64>"
    },
    "name": "upload_accounting_document"
  }
}

Input Schema

NameRequiredDescriptionDefault
forceNo
filenameYes
company_idYes
file_base64Yes
fiscal_yearNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.9/5.0
Behavior4/5

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

With no annotations, the description carries the burden and does disclose the two most important traits: the upload is queued (not synchronous) and there is duplicate-detection behavior implied by `force` re-reading an already-read file. It omits failure handling, file size limits, and any authorization/company-scope requirements.

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 dense clauses, front-loaded with purpose, then the async follow-up, then per-parameter notes. Every sentence adds information and nothing is repeated from the schema.

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

Completeness3/5

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

There are no annotations and no output schema, so the description should say what the upload returns (an id? a job/status?) and note constraints like size or duplicates in more detail. Routing the agent to `get_accounting_document` partly compensates for the missing output schema, but the definition still leaves a 5-parameter mutation under-explained.

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

Parameters3/5

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

Schema description coverage is 0%, so the description must explain all five parameters. It adds genuine meaning for `file_base64` (raw bytes, base64), `fiscal_year` (fallback when the file is silent) and `force` (re-read), but `company_id` and `filename` are left entirely to inference.

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

Purpose4/5

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

States a concrete verb (upload) and the exact document classes accepted (balance sheet, P&L, VAT return) plus supported formats (PDF, P&L PNG/JPEG, XLSX). That specificity distinguishes it from generic siblings like upload_document, though no sibling is named explicitly.

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?

Gives real when-to-use rules: use `fiscal_year` when the file itself doesn't state the year, and `force` only to re-read an already-read file. It also tells the agent this is asynchronous and to follow with `get_accounting_document`. It does not say how this differs from upload_accounting_import or upload_bank_statement.

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