Skip to main content
Glama
iseppo

e-arveldaja MCP Server

by iseppo
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

Process CAMT.053

process_camt053
Destructive

Parse CAMT.053 bank statements, preview transactions before import, and create approved transactions in e-arveldaja.

Instructions

Merged CAMT.053 entry point. Use mode='parse' to inspect a bank statement, mode='dry_run' to preview transaction import, or mode='execute' to create transactions after approval.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modeNoWorkflow phase to run. Defaults to parse.
date_toNoOnly import entries up to this date (YYYY-MM-DD)
file_refNoOpaque Accounting Inbox CAMT file reference. Provide exactly one of file_path or file_ref.
date_fromNoOnly import entries from this date (YYYY-MM-DD)
file_pathNoAbsolute path/base64 input. Provide exactly one of file_path or file_ref.
plan_handleNoExecution-plan handle returned by the reviewed dry run. Required for mode='execute'.
accounts_dimensions_idNoBank account dimension ID in e-arveldaja. Required for dry_run and execute modes.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.29.2
    • addedInput schema / additionalProperties
      Added value: +false
  2. Changed4 schema fields changedv0.25.2
    • changedInput schema / properties / file_path / description
      Previous value: -"Absolute path to the CAMT.053 XML file."New value: +"Absolute path/base64 input. Provide exactly one of file_path or file_ref."
    • addedInput schema / properties / file_ref
      Added value: +{
+  "description": "Opaque Accounting Inbox CAMT file reference. Provide exactly one of file_path or file_ref.",
+  "type": "string"
+}
    • addedInput schema / properties / plan_handle
      Added value: +{
+  "description": "Execution-plan handle returned by the reviewed dry run. Required for mode='execute'.",
+  "type": "string"
+}
    • removedInput schema / required
      Removed value: -[
-  "file_path"
-]
  3. First observedv0.18.1

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already carry the safety profile (destructive=true, idempotent=false, openWorld=true). The description adds meaningful workflow context beyond them: execute is gated behind an approved dry run, which tells the agent this is a staged, approval-driven mutation rather than a fire-and-forget write. It stops short of describing reversibility, return content, or failure modes.

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?

A single lead sentence plus one routing sentence, zero filler, and the mode-to-action mapping is front-loaded where the agent will read it first.

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 7-param, no-output-schema tool, the description adequately covers the mode workflow and the staged approval model. It does not address what parse/dry_run return or how file_path vs file_ref are expected to be supplied, but the schema descriptions cover those inputs, leaving only minor gaps.

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 100%, so the baseline is 3, but the description goes further by defining the semantic meaning of each mode enum value (inspect vs preview vs create), which the schema only labels generically as 'Workflow phase to run.' The file/date/plan parameters remain schema-only, so it does not fully earn a 5.

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?

The description names a specific resource (CAMT.053 bank statement) and frames the tool as the merged entry point for it, with three clearly enumerated modes. An agent can tell this apart from siblings like import_wise_transactions or parse_lightyear_statement by the CAMT.053 scope, 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 Guidelines5/5

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

It maps each mode to a concrete intent: parse to inspect, dry_run to preview import, execute to create transactions after approval. This effectively gives the agent the when-to-use condition for every alternative the tool offers, including the ordering constraint implied by 'after approval'.

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

Deploy Server

Other Tools