Skip to main content
Glama

Execute Plan

chaoscore_execute
Destructive

Execute plans or inline steps with per-step policy enforcement, dry-run validation, and approval confirmations, returning evaluation results.

Instructions

Run a plan (or inline steps) through the remaining stages of the Cognitive Core loop: policy check -> capability selection -> execution -> evaluation. This is the only tool in this server that can have side effects, and only insofar as the capabilities it invokes do.

Each step is policy-checked individually before it runs (ALLOW / DENY / REQUIRE_APPROVAL — see chaoscore_inspect target="policy"). Steps that are DENY, or REQUIRE_APPROVAL and not yet confirmed, are reported as failed/skipped rather than silently dropped — read each step's error field. Every policy decision and capability call is recorded to the audit trail (chaoscore_inspect target="audit"). This is identical over stdio and over remote HTTP: there is no transport that can reach a capability without passing the policy engine.

Args:

  • plan_id (string, optional): id from a prior chaoscore_plan call in this session

  • steps (array, optional): inline steps [{description, capability, input, rationale}], alternative to plan_id

  • confirmed (boolean): set true to also run steps that resolve to REQUIRE_APPROVAL (default: false)

  • dry_run (boolean): if true, validates policy + input schema per step without calling any handler (default: false)

  • response_format ('markdown' | 'json'): Output format (default: 'markdown')

Returns: For JSON format: { "planId": string, "objective": string, "steps": [ { "stepId": string, "capability": string, "success": boolean, "output"?: any, "error"?: string, "policyDecision": { "decision": "allow"|"deny"|"require_approval", "allowed": boolean, "requiresConfirmation": boolean, "reason": string }, "durationMs": number } ], "evaluation": { "success": boolean, "summary": string, "notes": string[] }, "completedAt": string }

Examples:

  • Use when: You have a plan_id from chaoscore_plan and are ready to run it -> chaoscore_execute(plan_id="...")

  • Use when: A step came back REQUIRE_APPROVAL and you've now confirmed with the user -> re-run with confirmed=true

  • Don't use when: You just want to see what a plan would do without side effects -> use dry_run=true

Error Handling:

  • Returns "Error: plan_id not found in this session" if the plan wasn't created in the current MCP session

  • Individual step failures do NOT throw — they appear in the steps array with success=false

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
stepsNoInline steps to execute directly, as an alternative to plan_id
dry_runNoIf true, validate policy + input schema for every step but never call any capability handler
plan_idNoid of a plan previously returned by chaoscore_plan in this MCP session
confirmedNoSet true to also run steps whose capability policy resolves to REQUIRE_APPROVAL
response_formatNoOutput format: 'markdown' for human-readable or 'json' for machine-readablemarkdown
Behavior5/5

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

The description discloses that the tool can have side effects, aligns with destructiveHint=true, and adds depth: each step is policy-checked individually, DENY/REQUIRE_APPROVAL steps are reported as failed/skipped, and all decisions are recorded to an audit trail. It even states transport invariance (stdio/HTTP) regarding policy enforcement, which is valuable context beyond the annotations.

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?

The description is long but every part serves a purpose: core functionality, policy details, parameter explanations, return structure, usage examples, and error handling. It is front-loaded with the primary purpose and logically organized. No wasted sentences.

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

Completeness5/5

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

The description is exhaustive for a complex tool: it covers side effects, policy behavior, both invocation modes, output format details, error handling (plan_id not found), and the fact that step failures don't throw. It even provides a full JSON response structure. Nothing an agent needs to call it correctly is missing.

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

Parameters5/5

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

While the schema already describes all parameters (100% coverage), the description adds meaningful nuance: the relationship between plan_id and steps (alternatives), the confirmed flag's role in running REQUIRE_APPROVAL steps, and the dry_run option to avoid side effects. It also clarifies the response_format's human vs. machine readability. This enriches the schema.

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

Purpose5/5

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

The description clearly states the tool's function: executing a plan or inline steps through the Cognitive Core loop. It distinguishes from siblings by noting it's the only tool that can have side effects, and it specifies the pipeline (policy check, capability selection, execution, evaluation). This is a specific verb+resource with clear differentiation.

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?

The description provides explicit usage scenarios: 'Use when: You have a plan_id from chaoscore_plan and are ready to run it', and 'Use when: A step came back REQUIRE_APPROVAL and you've now confirmed with the user'. It also gives a clear exclusion: 'Don't use when: You just want to see what a plan would do without side effects -> use dry_run=true'. This is excellent guidance.

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/chaosbrewing/chaos-core-mcp'

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