Skip to main content
Glama
Sign In
e-arveldaja MCP Server

e-arveldaja MCP Server

by iseppo
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

Continue Accounting Workflow

continue_accounting_workflow
Idempotent

Advance an e-arveldaja accounting workflow by moving to the next item, resolving review items, or preparing and executing approval actions.

Instructions

Continue an accounting workflow response, resolve a review item, or prepare an approval action.

Input Schema

NameRequiredDescriptionDefault
actionNonext reads workflow_handle (+ item_id) or workflow_state_json; resolve_review/prepare_action read review_item_json; execute_review_action books a prepared owner-expense continuation or records a prepared CAMT journal-review acknowledgement with plan_handle.
item_idNoStable id of a workflow item (from a workflow_action_v2 blocker or page item); action='next' returns the item after it.
plan_handleNoFor action='execute_review_action': the consume-once plan handle minted by action='prepare_action' for a server-executed owner-expense continuation or CAMT journal-review acknowledgement. Drift-bound to the reviewed booking params; not itself approval.
save_as_ruleNoFor action='prepare_action', prepare save_auto_booking_rule when appropriate.
workflow_handleNoOpaque server-issued workflow handle from a compact workflow_action_v2 response. Carries inert prior workflow state; never approval or mutation authority.
review_item_jsonNoReview item object for action='resolve_review' or action='prepare_action'.
rule_override_jsonNoOptional explicit rule fields for action='prepare_action'.
workflow_state_jsonNoPrevious v1 workflow response; required for action='next' without workflow_handle.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.39.0
    • changedInput schema / properties / action / description
      Previous value: -"next reads workflow_handle (+ item_id) or workflow_state_json; resolve_review/prepare_action read review_item_json; execute_review_action books a prepared owner-expense continuation with plan_handle."New value: +"next reads workflow_handle (+ item_id) or workflow_state_json; resolve_review/prepare_action read review_item_json; execute_review_action books a prepared owner-expense continuation or records a prepared CAMT journal-review acknowledgement with plan_handle."
    • changedInput schema / properties / plan_handle / description
      Previous value: -"For action='execute_review_action': the consume-once plan handle minted by action='prepare_action' for a server-executed owner-expense continuation. Drift-bound to the reviewed booking params; not itself approval."New value: +"For action='execute_review_action': the consume-once plan handle minted by action='prepare_action' for a server-executed owner-expense continuation or CAMT journal-review acknowledgement. Drift-bound to the reviewed booking params; not itself approval."
  2. Changed1 schema field changedv0.29.2
    • addedInput schema / additionalProperties
      Added value: +false
  3. Changed4 schema fields changedv0.27.0
    • changedInput schema / properties / action / description
      Previous value: -"next reads workflow_state_json; resolve_review/prepare_action read review_item_json; execute_review_action books a prepared owner-expense continuation with plan_handle."New value: +"next reads workflow_handle (+ item_id) or workflow_state_json; resolve_review/prepare_action read review_item_json; execute_review_action books a prepared owner-expense continuation with plan_handle."
    • removedInput schema / properties / answer
      Removed value: -{
-  "description": "Free-text answer to the current workflow question, for a compact guided continuation. Capped so a whole continuation stays within the 1 KiB budget.",
-  "maxLength": 700,
-  "type": "string"
-}
    • changedInput schema / properties / item_id / description
      Previous value: -"Stable id of the workflow item this continuation answers (from a workflow_action_v2 blocker or page item)."New value: +"Stable id of a workflow item (from a workflow_action_v2 blocker or page item); action='next' returns the item after it."
    • changedInput schema / properties / workflow_state_json / description
      Previous value: -"Previous workflow response; required for action='next'."New value: +"Previous v1 workflow response; required for action='next' without workflow_handle."
  4. Changed6 schema fields changedv0.25.2
    • changedInput schema / properties / action / description
      Previous value: -"next reads workflow_state_json; resolve_review/prepare_action read review_item_json."New value: +"next reads workflow_state_json; resolve_review/prepare_action read review_item_json; execute_review_action books a prepared owner-expense continuation with plan_handle."
    • changedInput schema / properties / action / enum
      Previous value: -[
-  "next",
-  "resolve_review",
-  "prepare_action"
-]New value: +[
+  "next",
+  "resolve_review",
+  "prepare_action",
+  "execute_review_action"
+]
    • addedInput schema / properties / answer
      Added value: +{
+  "description": "Free-text answer to the current workflow question, for a compact guided continuation. Capped so a whole continuation stays within the 1 KiB budget.",
+  "maxLength": 700,
+  "type": "string"
+}
    • addedInput schema / properties / item_id
      Added value: +{
+  "description": "Stable id of the workflow item this continuation answers (from a workflow_action_v2 blocker or page item).",
+  "maxLength": 128,
+  "type": "string"
+}
    • addedInput schema / properties / plan_handle
      Added value: +{
+  "description": "For action='execute_review_action': the consume-once plan handle minted by action='prepare_action' for a server-executed owner-expense continuation. Drift-bound to the reviewed booking params; not itself approval.",
+  "pattern": "^[A-Za-z0-9_-]{43}$",
+  "type": "string"
+}
    • addedInput schema / properties / workflow_handle
      Added value: +{
+  "description": "Opaque server-issued workflow handle from a compact workflow_action_v2 response. Carries inert prior workflow state; never approval or mutation authority.",
+  "pattern": "^[A-Za-z0-9_-]{43}$",
+  "type": "string"
+}
  5. First observedv0.18.1

TDQS

C2.6/5.0
Behavior2/5

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

Annotations already declare readOnlyHint=false, idempotentHint=true, destructiveHint=false, so the safety profile is partly covered. However, the description never states that 'execute_review_action' performs a booking/acknowledgement mutation, that plan handles are consume-once, or that handles carry no approval authority — all of that behavioral context lives only in the schema property text, leaving the description silent on the one thing that matters most for a mutating tool.

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?

One short sentence with no padding, front-loaded with the verb. It is efficient, though the brevity tips into under-specification rather than crispness because the three listed clauses overlap and are not parallel to the action enum.

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

Completeness2/5

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

This is an 8-parameter, four-action, mutating workflow tool with no output schema, and the description covers only three of the four actions with no explanation of how the actions relate or how to pick one. The rich schema compensates somewhat, but the description does not carry enough to make the tool safely selectable on its own.

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% and the property descriptions are unusually detailed (handle semantics, plan_handle drift-binding, per-action requirements). The description adds essentially nothing beyond restating two of the actions, so the baseline 3 for full schema coverage is the right ceiling.

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

Purpose3/5

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

The description names three modes (continue a workflow response, resolve a review item, prepare an approval action), which loosely maps to the action enum, but the phrasing is vague and it omits the fourth enum value 'execute_review_action', which actually books transactions. An agent cannot fully tell what the tool does from the sentence alone without reading the schema.

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

Usage Guidelines2/5

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

No when-to-use guidance, no prerequisites, and no routing to any sibling. With ~120 siblings including recommend_workflow, get_execution_plan_page, and get_operation_result_page, the definition gives no signal about when this workflow-continuation tool is the right call versus those alternatives.

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