Skip to main content
Glama
iseppo

e-arveldaja MCP Server

by iseppo
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

Classify Bank Transactions

classify_bank_transactions
Destructive

Classify unmatched bank transactions into groups, preview the classification plan, and apply approved matches to reconcile bank accounts.

Instructions

Merged unmatched-bank classification. classify groups; dry_run_apply previews; execute_apply requires approval.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modeNoWorkflow phase to run. Defaults to classify.
date_toNoOptional upper transaction date bound for mode='classify' (YYYY-MM-DD).
date_fromNoOptional lower transaction date bound for mode='classify' (YYYY-MM-DD).
plan_handleNoConsume-once handle returned by mode='dry_run_apply'. REQUIRED for mode='execute_apply'.
classifications_jsonNoStructured output from mode='classify'. Required for apply modes.
accounts_dimensions_idNoBank account dimension ID. Required for mode='classify'.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.29.2
    • addedInput schema / additionalProperties
      Added value: +false
  2. Changed1 schema field changedv0.25.2
    • addedInput schema / properties / plan_handle
      Added value: +{
+  "description": "Consume-once handle returned by mode='dry_run_apply'. REQUIRED for mode='execute_apply'.",
+  "type": "string"
+}
  3. First observedv0.18.1

TDQS

B3.4/5.0
Behavior3/5

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

Annotations already disclose destructiveHint=true and idempotentHint=false, so the safety profile is partly covered. The description adds value by flagging that execute_apply 'requires approval' and that dry_run_apply is only a preview, but it never says what execute_apply actually mutates or whether its effects are reversible, leaving the destructive flag uncontextualized.

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?

It is a single compact line with no filler, and the mode breakdown follows the opening purpose statement. The lead fragment 'Merged unmatched-bank classification' is opaque internal jargon rather than a clean front-load, which keeps it out of the top band.

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?

For a six-parameter, three-phase workflow tool with a destructive apply step and no output schema, the description covers only the mode names. It omits the data flow between phases (classifications_json and the consume-once plan_handle lifecycle) and any post-apply outcome, leaving real workflow gaps.

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 100%, so the baseline is 3. The description reinforces the mode semantics that drive which parameters matter (classify vs apply, plan_handle, classifications_json), but adds no syntax or format detail beyond the schema.

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 name plus 'Merged unmatched-bank classification' makes it clear this tool classifies bank transactions, and the three mode clauses sharpen the verb into concrete phases. It does not, however, distinguish itself from adjacent siblings like reconcile_bank_transactions or analyze_unconfirmed_transactions, so an agent must infer the boundary.

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?

The phrase 'classify groups; dry_run_apply previews; execute_apply requires approval' implies the intended phase order and the safety gate on the final phase. There is no explicit statement of when to prefer this tool over reconcile_bank_transactions, nor of preconditions such as needing classify output before apply.

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