Skip to main content
Glama

cmmn-create_task

cmmn-create_task

Create a CMMN task with lifecycle states, decision support, and automated sentry triggers for case management workflows.

Instructions

Creates a CMMN-aligned task with lifecycle state management

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
auto_complete_on_sub_caseNoAutomatically complete this task when sub-case completes (default: true)
assigned_toNoWho/what is responsible (user, agent, system)
titleYesTask title/summary
required_evidenceNoEvidence-key names the agent must supply on completion (e.g. ['migration_file_path', 'test_file_path']). Optional.
estimated_hoursNoEstimated effort in hours
contextNoWorking notes, reasoning, approach for AI resumption
decision_typeNoHow to evaluate: expression, table, ai, external
requiredNoIs this task required for parent stage auto-complete? Default: true
process_definition_idNoProcess definition ID to execute (for task_type='process')
output_mappingNoMap sub-case results back to parent task (keys are parent field names)
case_model_idNoCasePlanModel ID to instantiate when task becomes active (only for task_type='case')
triggers_sentry_on_outcomeNoMap of outcome values to sentry IDs. When decision produces an outcome, triggers corresponding sentry.
decision_expressionNoExpression to evaluate (for decision_type='expression'). Supports: 'amount > 1000', 'status == approved', 'count in [1, 2, 3]'
exit_criteriaNoConditions that must be met to complete (legacy free-form list — use acceptance_criteria for judge-layer verification)
entry_criteriaNoConditions that must be met to start
input_mappingNoMap parent case data to sub-case (keys are sub-case field names)
input_dataNoInput variables for the process (for task_type='process')
sub_case_nameNoName for the sub-case (defaults to task title if not specified)
task_typeNoCMMN task type: human, process, case, decision
case_idYesCase ID (@rid format)
due_dateNoTarget completion date (ISO8601)
descriptionNoDetailed task description
priorityNoPriority: critical, high, medium, low
statusYesCMMN lifecycle state: available, enabled, disabled, active, suspended, completed, terminated, failed
decision_descriptionNoNatural language description (for decision_type='ai'). AI will evaluate and return outcome.
created_byNoWho created this task
parent_idNoParent item ID (for hierarchical nesting)
next_stepsNoPlanned next actions
blocked_byNoWhat is currently blocking this task
decision_tableNoDecision table rules (for decision_type='table'). Array of {conditions: {var: val}, outcome: 'result'}
acceptance_criteriaNoJudge-layer acceptance criteria. Each item is {id, text, verifier}. verifier is a registered check name (schema_check, file_exists, command_runs_clean, ...) or 'manual'. Workflow author attaches these so the runtime judge can evaluate task completion claims.
decision_inputsNoInput variables for decision evaluation. Keys are variable names, values are the data.
depends_onNoTask IDs this task depends on
auto_complete_on_decisionNoAutomatically complete this task when decision is made (default: true)
Behavior2/5

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

With no annotations, the description must disclose behavioral traits. It only states 'creates', implying mutation, but lacks details on side effects, permissions, or lifecycle implications beyond the status parameter.

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?

Single-sentence description is efficient and front-loaded. However, for a tool with 34 parameters, slightly more detail would improve usability without becoming verbose.

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?

Given the complexity (34 parameters, no output schema), the description is insufficient. It omits return values, examples, and relationships to other cmmn tools, leaving the agent with limited guidance.

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?

All 34 parameters have schema descriptions, achieving 100% coverage. The description adds no additional parameter information, meeting the baseline but not exceeding it.

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?

Description clearly states the tool creates a CMMN-aligned task and references lifecycle state management, distinguishing it from siblings like cmmn-complete_task. However, 'CMMN-aligned' could be further clarified for agents unfamiliar with CMMN.

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 guidance on when to use this tool versus alternatives (e.g., cmmn-create_stage, cmmn-complete_task). The description does not specify context or exclusions.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/mstang/casemgr-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server