Skip to main content
Glama
harness

Harness MCP Server

Official
by harness
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

harness_execute

Destructive

Run Harness actions such as pipelines, feature flags, connector tests, GitOps syncs, and chaos experiments. Pass a Harness URL to auto-extract IDs, or wait=true to block until completion.

Instructions

Execute an action on a Harness resource: run/retry/interrupt pipelines, kill/restore FME feature flags, test connectors, sync GitOps apps, run chaos experiments. You can pass a Harness URL to auto-extract identifiers. Pass wait: true for pipeline run/retry to block until the execution reaches a terminal status — single tool call instead of an LLM polling loop. For HQL batch operations pass queries with resource_type='hql_query' and action='validate' or 'run'.

Input Schema

NameRequiredDescriptionDefault
urlNoHarness UI URL — auto-extracts org, project, type, and ID
bodyNoAdditional body payload for the action
waitNoPipeline run/retry only: block until the execution reaches a terminal status (server-side polling).
actionYesAction to execute (e.g. run, retry, interrupt, toggle, test_connection, sync)
inputsNoPipeline runtime inputs (key-value pairs or overlay YAML). Check runtime_input_template (v0) or runtime_input_template_v1 first.
org_idNoOrg identifier. Required unless a Harness URL is passed (no configured default).
paramsNoAction-specific parameters. Call harness_describe for available fields per resource_type.
confirmNoUser-approved confirmation for medium/high-risk operations when the client cannot show a prompt. Set only with user intent; never overrides a user's decline.
queriesNoBatch HQL queries for resource_type='hql_query' with action validate or run; run in parallel.
project_idNoProject identifier. Required for project-scoped resources unless a Harness URL is passed (no configured default).
resource_idNoPrimary resource identifier
input_set_idsNoInput set IDs for complex pipelines. List available: harness_list(resource_type='input_set', filters={pipeline_id: '...'}).
resource_typeNoResource type with executable actions. Auto-detected from url.
resource_scopeNoaccount|org|project. Omit for the resource's default scope. Never use account to skip a known org/project. Auto-detected from url.
wait_timeout_secondsNoMax seconds to wait when wait=true (default 600). On timeout returns execution_timed_out=true.
wait_poll_interval_secondsNoInitial poll interval when wait=true (default 3s, 1.5x backoff, capped at 30s).

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed12 schema fields changedv3.2.35
    • changedInput schema / properties / confirm / description
      Previous value: -"Set to true to confirm the operation. Only required when the action's risk is medium_write or above (e.g. pipeline.run is high_write; hql_query.run/validate are read and need no confirmation) AND the client cannot surface a confirmation prompt — e.g. managed MCP that does not advertise elicitation, or an elicitation that fails at runtime. Has no effect for low-risk actions. Does NOT override an explicit decline from a client that completed an elicitation prompt — a user's decline is authoritative."New value: +"User-approved confirmation for medium/high-risk operations when the client cannot show a prompt. Set only with user intent; never overrides a user's decline."
    • changedInput schema / properties / inputs / description
      Previous value: -"Pipeline runtime inputs. For v0 pipeline, check runtime_input_template and pass key-value pairs or full overlay YAML. For pipeline_v1, check runtime_input_template_v1 and pass named values; the server sends them as an inputs: YAML document."New value: +"Pipeline runtime inputs (key-value pairs or overlay YAML). Check runtime_input_template (v0) or runtime_input_template_v1 first."
    • changedInput schema / properties / org_id / description
      Previous value: -"Organization identifier. Required for org- and project-scoped resources unless a Harness URL is passed. This session has no configured default (common in hosted/multi-user HTTP) — pass the current org_id on the first call. Do not omit it."New value: +"Org identifier. Required unless a Harness URL is passed (no configured default)."
    • changedInput schema / properties / project_id / description
      Previous value: -"Project identifier. Required for project-scoped resources unless a Harness URL is passed. This session has no configured default (common in hosted/multi-user HTTP) — pass the current project_id on the first call. Do not omit it."New value: +"Project identifier. Required for project-scoped resources unless a Harness URL is passed (no configured default)."
    • changedInput schema / properties / queries / description
      Previous value: -"Batch HQL queries — use with resource_type='hql_query' and action='validate' or 'run'. Fans out in parallel, returns per-query results."New value: +"Batch HQL queries for resource_type='hql_query' with action validate or run; run in parallel."
    • changedInput schema / properties / resource_scope / description
      Previous value: -"Scope for the operation. account: account-level resources only — do not use account to skip a known org/project. org: org-level (org_id). project: org+project. Omit to use the resource's default scope. Auto-detected from url when present."New value: +"account|org|project. Omit for the resource's default scope. Never use account to skip a known org/project. Auto-detected from url."
    • removedInput schema / properties / resource_type / enum
      Removed value: -[
-  "activity_timeline",
-  "ai_budget_override_request",
-  "alert",
-  "approval_instance",
-  "attestation",
-  "chaos_action",
-  "chaos_action_template",
-  "chaos_experiment",
-  "chaos_experiment_template",
-  "chaos_fault",
-  "chaos_fault_template",
-  "chaos_guard_rule",
-  "chaos_k8s_infrastructure",
-  "chaos_loadtest",
-  "chaos_probe",
-  "chaos_probe_template",
-  "chaos_risk_scan",
-  "chaos_service",
-  "commit",
-  "connector",
-  "cost_anomaly",
-  "cost_budget",
-  "cost_perspective",
-  "cost_perspective_folder",
-  "cost_recommendation",
-  "database_execute_llm_authoring_pipeline",
-  "delegate_token",
-  "environment",
-  "eval_annotation",
-  "eval_dataset",
-  "eval_dataset_item",
-  "eval_git_registration",
-  "eval_metric",
-  "eval_metric_set",
-  "eval_run",
-  "eval_suite",
-  "eval_target",
-  "evaluation",
-  "execution",
-  "file_content",
-  "file_store",
-  "fme_feature_flag",
-  "fme_feature_flag_definition",
-  "fme_rule_based_segment_definition",
-  "fme_segment_definition",
-  "freeze_window",
-  "gitops_app_project_mapping",
-  "gitops_application",
-  "global_freeze",
-  "hql_query",
-  "idp_workflow",
-  "incident",
-  "infrastructure",
-  "online_eval",
-  "pipeline",
-  "pipeline_dynamic_execution",
-  "pipeline_v1",
-  "pr_comment",
-  "pr_reviewer",
-  "pull_request",
-  "scanned_risk",
-  "scs_sbom_drift",
-  "security_exemption",
-  "user",
-  "vibe_app_lifecycle",
-  "vibe_project"
-]
    • addedInput schema / properties / resource_type / minLength
      Added value: +1
    • changedInput schema / properties / wait / description
      Previous value: -"For pipeline run/retry actions: block until the execution reaches a terminal status (Success/Failed/Aborted/Errored/Expired). Server-side polling — a single tool call gives the agent the final outcome instead of an LLM polling loop. Ignored for other actions."New value: +"Pipeline run/retry only: block until the execution reaches a terminal status (server-side polling)."
    • changedInput schema / properties / wait_poll_interval_seconds / description
      Previous value: -"Initial poll interval when wait=true (seconds). Default 3. Backoff multiplier 1.5x, capped at 30s."New value: +"Initial poll interval when wait=true (default 3s, 1.5x backoff, capped at 30s)."
    • changedInput schema / properties / wait_timeout_seconds / description
      Previous value: -"Max seconds to wait when wait=true. Default 600 (10 min). Max 7200 (2 h). When the timeout fires, returns execution_timed_out=true with the last observed status."New value: +"Max seconds to wait when wait=true (default 600). On timeout returns execution_timed_out=true."
    • removedOutput schema / description
      Removed value: -"Execution result — shape varies by action and resource_type"
  2. Changed1 schema field changedv3.2.31
    • changedInput schema / properties / resource_type / enum
      Previous value: -[
-  "ai_budget_override_request",
-  "alert",
-  "approval_instance",
-  "attestation",
-  "chaos_action",
-  "chaos_action_template",
-  "chaos_experiment",
-  "chaos_experiment_template",
-  "chaos_fault",
-  "chaos_fault_template",
-  "chaos_guard_rule",
-  "chaos_k8s_infrastructure",
-  "chaos_loadtest",
-  "chaos_probe",
-  "chaos_probe_template",
-  "chaos_risk_scan",
-  "chaos_service",
-  "commit",
-  "connector",
-  "cost_anomaly",
-  "cost_budget",
-  "cost_perspective",
-  "cost_perspective_folder",
-  "cost_recommendation",
-  "database_execute_llm_authoring_pipeline",
-  "delegate_token",
-  "environment",
-  "eval_annotation",
-  "eval_dataset",
-  "eval_dataset_item",
-  "eval_git_registration",
-  "eval_metric",
-  "eval_metric_set",
-  "eval_run",
-  "eval_suite",
-  "eval_target",
-  "evaluation",
-  "execution",
-  "file_content",
-  "file_store",
-  "fme_feature_flag",
-  "fme_feature_flag_definition",
-  "fme_rule_based_segment_definition",
-  "fme_segment_definition",
-  "freeze_window",
-  "gitops_application",
-  "global_freeze",
-  "hql_query",
-  "idp_workflow",
-  "incident",
-  "infrastructure",
-  "online_eval",
-  "pipeline",
-  "pipeline_dynamic_execution",
-  "pipeline_v1",
-  "pr_reviewer",
-  "pull_request",
-  "scanned_risk",
-  "scs_sbom_drift",
-  "security_exemption",
-  "user",
-  "vibe_app_lifecycle",
-  "vibe_project"
-]New value: +[
+  "activity_timeline",
+  "ai_budget_override_request",
+  "alert",
+  "approval_instance",
+  "attestation",
+  "chaos_action",
+  "chaos_action_template",
+  "chaos_experiment",
+  "chaos_experiment_template",
+  "chaos_fault",
+  "chaos_fault_template",
+  "chaos_guard_rule",
+  "chaos_k8s_infrastructure",
+  "chaos_loadtest",
+  "chaos_probe",
+  "chaos_probe_template",
+  "chaos_risk_scan",
+  "chaos_service",
+  "commit",
+  "connector",
+  "cost_anomaly",
+  "cost_budget",
+  "cost_perspective",
+  "cost_perspective_folder",
+  "cost_recommendation",
+  "database_execute_llm_authoring_pipeline",
+  "delegate_token",
+  "environment",
+  "eval_annotation",
+  "eval_dataset",
+  "eval_dataset_item",
+  "eval_git_registration",
+  "eval_metric",
+  "eval_metric_set",
+  "eval_run",
+  "eval_suite",
+  "eval_target",
+  "evaluation",
+  "execution",
+  "file_content",
+  "file_store",
+  "fme_feature_flag",
+  "fme_feature_flag_definition",
+  "fme_rule_based_segment_definition",
+  "fme_segment_definition",
+  "freeze_window",
+  "gitops_app_project_mapping",
+  "gitops_application",
+  "global_freeze",
+  "hql_query",
+  "idp_workflow",
+  "incident",
+  "infrastructure",
+  "online_eval",
+  "pipeline",
+  "pipeline_dynamic_execution",
+  "pipeline_v1",
+  "pr_comment",
+  "pr_reviewer",
+  "pull_request",
+  "scanned_risk",
+  "scs_sbom_drift",
+  "security_exemption",
+  "user",
+  "vibe_app_lifecycle",
+  "vibe_project"
+]
  3. Changed1 schema field changedv3.2.28
    • changedInput schema / properties / resource_type / enum
      Previous value: -[
-  "alert",
-  "approval_instance",
-  "attestation",
-  "chaos_action",
-  "chaos_action_template",
-  "chaos_experiment",
-  "chaos_experiment_template",
-  "chaos_fault",
-  "chaos_fault_template",
-  "chaos_guard_rule",
-  "chaos_k8s_infrastructure",
-  "chaos_loadtest",
-  "chaos_probe",
-  "chaos_probe_template",
-  "chaos_risk_scan",
-  "chaos_service",
-  "commit",
-  "connector",
-  "cost_anomaly",
-  "cost_budget",
-  "cost_perspective",
-  "cost_perspective_folder",
-  "cost_recommendation",
-  "database_execute_llm_authoring_pipeline",
-  "delegate_token",
-  "environment",
-  "eval_annotation",
-  "eval_dataset",
-  "eval_dataset_item",
-  "eval_git_registration",
-  "eval_metric",
-  "eval_metric_set",
-  "eval_run",
-  "eval_suite",
-  "eval_target",
-  "evaluation",
-  "execution",
-  "file_content",
-  "file_store",
-  "fme_feature_flag",
-  "fme_feature_flag_definition",
-  "fme_rule_based_segment_definition",
-  "fme_segment_definition",
-  "freeze_window",
-  "gitops_application",
-  "global_freeze",
-  "hql_query",
-  "idp_workflow",
-  "incident",
-  "infrastructure",
-  "online_eval",
-  "pipeline",
-  "pipeline_dynamic_execution",
-  "pipeline_v1",
-  "pr_reviewer",
-  "pull_request",
-  "scanned_risk",
-  "scs_sbom_drift",
-  "security_exemption",
-  "user",
-  "vibe_app_lifecycle",
-  "vibe_project"
-]New value: +[
+  "ai_budget_override_request",
+  "alert",
+  "approval_instance",
+  "attestation",
+  "chaos_action",
+  "chaos_action_template",
+  "chaos_experiment",
+  "chaos_experiment_template",
+  "chaos_fault",
+  "chaos_fault_template",
+  "chaos_guard_rule",
+  "chaos_k8s_infrastructure",
+  "chaos_loadtest",
+  "chaos_probe",
+  "chaos_probe_template",
+  "chaos_risk_scan",
+  "chaos_service",
+  "commit",
+  "connector",
+  "cost_anomaly",
+  "cost_budget",
+  "cost_perspective",
+  "cost_perspective_folder",
+  "cost_recommendation",
+  "database_execute_llm_authoring_pipeline",
+  "delegate_token",
+  "environment",
+  "eval_annotation",
+  "eval_dataset",
+  "eval_dataset_item",
+  "eval_git_registration",
+  "eval_metric",
+  "eval_metric_set",
+  "eval_run",
+  "eval_suite",
+  "eval_target",
+  "evaluation",
+  "execution",
+  "file_content",
+  "file_store",
+  "fme_feature_flag",
+  "fme_feature_flag_definition",
+  "fme_rule_based_segment_definition",
+  "fme_segment_definition",
+  "freeze_window",
+  "gitops_application",
+  "global_freeze",
+  "hql_query",
+  "idp_workflow",
+  "incident",
+  "infrastructure",
+  "online_eval",
+  "pipeline",
+  "pipeline_dynamic_execution",
+  "pipeline_v1",
+  "pr_reviewer",
+  "pull_request",
+  "scanned_risk",
+  "scs_sbom_drift",
+  "security_exemption",
+  "user",
+  "vibe_app_lifecycle",
+  "vibe_project"
+]
  4. Changed1 schema field changedv3.2.26
    • changedInput schema / properties / resource_type / enum
      Previous value: -[
-  "alert",
-  "approval_instance",
-  "attestation",
-  "chaos_action",
-  "chaos_action_template",
-  "chaos_experiment",
-  "chaos_experiment_template",
-  "chaos_fault",
-  "chaos_fault_template",
-  "chaos_guard_rule",
-  "chaos_k8s_infrastructure",
-  "chaos_loadtest",
-  "chaos_probe",
-  "chaos_probe_template",
-  "chaos_risk_scan",
-  "chaos_service",
-  "commit",
-  "connector",
-  "cost_anomaly",
-  "cost_budget",
-  "cost_perspective",
-  "cost_perspective_folder",
-  "cost_recommendation",
-  "database_execute_llm_authoring_pipeline",
-  "delegate_token",
-  "environment",
-  "eval_annotation",
-  "eval_dataset",
-  "eval_dataset_item",
-  "eval_git_registration",
-  "eval_metric",
-  "eval_metric_set",
-  "eval_run",
-  "eval_suite",
-  "eval_target",
-  "evaluation",
-  "execution",
-  "file_content",
-  "file_store",
-  "fme_feature_flag",
-  "fme_feature_flag_definition",
-  "fme_rule_based_segment_definition",
-  "freeze_window",
-  "gitops_application",
-  "global_freeze",
-  "hql_query",
-  "idp_workflow",
-  "incident",
-  "infrastructure",
-  "online_eval",
-  "pipeline",
-  "pipeline_dynamic_execution",
-  "pipeline_v1",
-  "pr_reviewer",
-  "pull_request",
-  "scanned_risk",
-  "scs_sbom_drift",
-  "security_exemption",
-  "user"
-]New value: +[
+  "alert",
+  "approval_instance",
+  "attestation",
+  "chaos_action",
+  "chaos_action_template",
+  "chaos_experiment",
+  "chaos_experiment_template",
+  "chaos_fault",
+  "chaos_fault_template",
+  "chaos_guard_rule",
+  "chaos_k8s_infrastructure",
+  "chaos_loadtest",
+  "chaos_probe",
+  "chaos_probe_template",
+  "chaos_risk_scan",
+  "chaos_service",
+  "commit",
+  "connector",
+  "cost_anomaly",
+  "cost_budget",
+  "cost_perspective",
+  "cost_perspective_folder",
+  "cost_recommendation",
+  "database_execute_llm_authoring_pipeline",
+  "delegate_token",
+  "environment",
+  "eval_annotation",
+  "eval_dataset",
+  "eval_dataset_item",
+  "eval_git_registration",
+  "eval_metric",
+  "eval_metric_set",
+  "eval_run",
+  "eval_suite",
+  "eval_target",
+  "evaluation",
+  "execution",
+  "file_content",
+  "file_store",
+  "fme_feature_flag",
+  "fme_feature_flag_definition",
+  "fme_rule_based_segment_definition",
+  "fme_segment_definition",
+  "freeze_window",
+  "gitops_application",
+  "global_freeze",
+  "hql_query",
+  "idp_workflow",
+  "incident",
+  "infrastructure",
+  "online_eval",
+  "pipeline",
+  "pipeline_dynamic_execution",
+  "pipeline_v1",
+  "pr_reviewer",
+  "pull_request",
+  "scanned_risk",
+  "scs_sbom_drift",
+  "security_exemption",
+  "user",
+  "vibe_app_lifecycle",
+  "vibe_project"
+]
  5. Changed1 schema field changedv3.2.25
    • changedInput schema / properties / inputs / description
      Previous value: -"Pipeline runtime inputs: key-value pairs like {branch: 'main'} (auto-resolved), or full YAML string. Check runtime_input_template first via harness_get."New value: +"Pipeline runtime inputs. For v0 pipeline, check runtime_input_template and pass key-value pairs or full overlay YAML. For pipeline_v1, check runtime_input_template_v1 and pass named values; the server sends them as an inputs: YAML document."
  6. Changed4 schema fields changedv3.2.22
    • changedInput schema / properties / org_id / description
      Previous value: -"Organization identifier (overrides default)"New value: +"Organization identifier. Required for org- and project-scoped resources unless a Harness URL is passed. This session has no configured default (common in hosted/multi-user HTTP) — pass the current org_id on the first call. Do not omit it."
    • changedInput schema / properties / project_id / description
      Previous value: -"Project identifier (overrides default)"New value: +"Project identifier. Required for project-scoped resources unless a Harness URL is passed. This session has no configured default (common in hosted/multi-user HTTP) — pass the current project_id on the first call. Do not omit it."
    • changedInput schema / properties / resource_scope / description
      Previous value: -"Scope for the operation. account: omit org/project (e.g. /v1/templates). org: org only. project: org+project. Auto-detected from url when present."New value: +"Scope for the operation. account: account-level resources only — do not use account to skip a known org/project. org: org-level (org_id). project: org+project. Omit to use the resource's default scope. Auto-detected from url when present."
    • changedInput schema / properties / resource_type / enum
      Previous value: -[
-  "approval_instance",
-  "attestation",
-  "chaos_action",
-  "chaos_action_template",
-  "chaos_experiment",
-  "chaos_experiment_template",
-  "chaos_fault",
-  "chaos_fault_template",
-  "chaos_guard_rule",
-  "chaos_k8s_infrastructure",
-  "chaos_loadtest",
-  "chaos_probe",
-  "chaos_probe_template",
-  "chaos_risk_scan",
-  "chaos_service",
-  "commit",
-  "connector",
-  "cost_anomaly",
-  "cost_budget",
-  "cost_perspective",
-  "cost_perspective_folder",
-  "cost_recommendation",
-  "database_execute_llm_authoring_pipeline",
-  "delegate_token",
-  "environment",
-  "eval_annotation",
-  "eval_dataset",
-  "eval_dataset_item",
-  "eval_git_registration",
-  "eval_metric",
-  "eval_metric_set",
-  "eval_run",
-  "eval_suite",
-  "eval_target",
-  "evaluation",
-  "execution",
-  "file_content",
-  "file_store",
-  "fme_feature_flag",
-  "fme_feature_flag_definition",
-  "fme_rule_based_segment_definition",
-  "freeze_window",
-  "gitops_application",
-  "global_freeze",
-  "hql_query",
-  "idp_workflow",
-  "incident",
-  "infrastructure",
-  "online_eval",
-  "pipeline",
-  "pipeline_dynamic_execution",
-  "pipeline_v1",
-  "pr_reviewer",
-  "pull_request",
-  "scanned_risk",
-  "scs_sbom_drift",
-  "security_exemption",
-  "user"
-]New value: +[
+  "alert",
+  "approval_instance",
+  "attestation",
+  "chaos_action",
+  "chaos_action_template",
+  "chaos_experiment",
+  "chaos_experiment_template",
+  "chaos_fault",
+  "chaos_fault_template",
+  "chaos_guard_rule",
+  "chaos_k8s_infrastructure",
+  "chaos_loadtest",
+  "chaos_probe",
+  "chaos_probe_template",
+  "chaos_risk_scan",
+  "chaos_service",
+  "commit",
+  "connector",
+  "cost_anomaly",
+  "cost_budget",
+  "cost_perspective",
+  "cost_perspective_folder",
+  "cost_recommendation",
+  "database_execute_llm_authoring_pipeline",
+  "delegate_token",
+  "environment",
+  "eval_annotation",
+  "eval_dataset",
+  "eval_dataset_item",
+  "eval_git_registration",
+  "eval_metric",
+  "eval_metric_set",
+  "eval_run",
+  "eval_suite",
+  "eval_target",
+  "evaluation",
+  "execution",
+  "file_content",
+  "file_store",
+  "fme_feature_flag",
+  "fme_feature_flag_definition",
+  "fme_rule_based_segment_definition",
+  "freeze_window",
+  "gitops_application",
+  "global_freeze",
+  "hql_query",
+  "idp_workflow",
+  "incident",
+  "infrastructure",
+  "online_eval",
+  "pipeline",
+  "pipeline_dynamic_execution",
+  "pipeline_v1",
+  "pr_reviewer",
+  "pull_request",
+  "scanned_risk",
+  "scs_sbom_drift",
+  "security_exemption",
+  "user"
+]
  7. Changed1 schema field changedv3.2.21
    • changedInput schema / properties / resource_type / enum
      Previous value: -[
-  "approval_instance",
-  "attestation",
-  "chaos_action",
-  "chaos_action_template",
-  "chaos_experiment",
-  "chaos_experiment_template",
-  "chaos_fault",
-  "chaos_fault_template",
-  "chaos_guard_rule",
-  "chaos_k8s_infrastructure",
-  "chaos_loadtest",
-  "chaos_probe",
-  "chaos_probe_template",
-  "chaos_risk_scan",
-  "chaos_service",
-  "commit",
-  "connector",
-  "cost_anomaly",
-  "cost_budget",
-  "cost_perspective",
-  "cost_perspective_folder",
-  "cost_recommendation",
-  "database_execute_llm_authoring_pipeline",
-  "delegate_token",
-  "environment",
-  "eval_annotation",
-  "eval_dataset",
-  "eval_dataset_item",
-  "eval_git_registration",
-  "eval_metric",
-  "eval_metric_set",
-  "eval_run",
-  "eval_suite",
-  "eval_target",
-  "evaluation",
-  "execution",
-  "file_content",
-  "file_store",
-  "fme_feature_flag",
-  "fme_rule_based_segment_definition",
-  "freeze_window",
-  "gitops_application",
-  "global_freeze",
-  "hql_query",
-  "idp_workflow",
-  "incident",
-  "infrastructure",
-  "online_eval",
-  "pipeline",
-  "pipeline_dynamic_execution",
-  "pipeline_v1",
-  "pr_reviewer",
-  "pull_request",
-  "scanned_risk",
-  "scs_sbom_drift",
-  "security_exemption",
-  "user"
-]New value: +[
+  "approval_instance",
+  "attestation",
+  "chaos_action",
+  "chaos_action_template",
+  "chaos_experiment",
+  "chaos_experiment_template",
+  "chaos_fault",
+  "chaos_fault_template",
+  "chaos_guard_rule",
+  "chaos_k8s_infrastructure",
+  "chaos_loadtest",
+  "chaos_probe",
+  "chaos_probe_template",
+  "chaos_risk_scan",
+  "chaos_service",
+  "commit",
+  "connector",
+  "cost_anomaly",
+  "cost_budget",
+  "cost_perspective",
+  "cost_perspective_folder",
+  "cost_recommendation",
+  "database_execute_llm_authoring_pipeline",
+  "delegate_token",
+  "environment",
+  "eval_annotation",
+  "eval_dataset",
+  "eval_dataset_item",
+  "eval_git_registration",
+  "eval_metric",
+  "eval_metric_set",
+  "eval_run",
+  "eval_suite",
+  "eval_target",
+  "evaluation",
+  "execution",
+  "file_content",
+  "file_store",
+  "fme_feature_flag",
+  "fme_feature_flag_definition",
+  "fme_rule_based_segment_definition",
+  "freeze_window",
+  "gitops_application",
+  "global_freeze",
+  "hql_query",
+  "idp_workflow",
+  "incident",
+  "infrastructure",
+  "online_eval",
+  "pipeline",
+  "pipeline_dynamic_execution",
+  "pipeline_v1",
+  "pr_reviewer",
+  "pull_request",
+  "scanned_risk",
+  "scs_sbom_drift",
+  "security_exemption",
+  "user"
+]
  8. Changed1 schema field changedv3.2.20
    • changedInput schema / properties / resource_type / enum
      Previous value: -[
-  "approval_instance",
-  "chaos_action",
-  "chaos_action_template",
-  "chaos_experiment",
-  "chaos_experiment_template",
-  "chaos_fault",
-  "chaos_fault_template",
-  "chaos_guard_rule",
-  "chaos_k8s_infrastructure",
-  "chaos_loadtest",
-  "chaos_probe",
-  "chaos_probe_template",
-  "chaos_risk_scan",
-  "commit",
-  "connector",
-  "cost_anomaly",
-  "cost_perspective",
-  "cost_perspective_folder",
-  "cost_recommendation",
-  "database_execute_llm_authoring_pipeline",
-  "delegate_token",
-  "environment",
-  "eval_annotation",
-  "eval_dataset",
-  "eval_dataset_item",
-  "eval_git_registration",
-  "eval_metric",
-  "eval_metric_set",
-  "eval_run",
-  "eval_suite",
-  "eval_target",
-  "evaluation",
-  "execution",
-  "file_content",
-  "file_store",
-  "fme_feature_flag",
-  "fme_rule_based_segment_definition",
-  "freeze_window",
-  "gitops_application",
-  "global_freeze",
-  "hql_query",
-  "idp_workflow",
-  "incident",
-  "infrastructure",
-  "online_eval",
-  "pipeline",
-  "pipeline_dynamic_execution",
-  "pipeline_v1",
-  "pr_reviewer",
-  "pull_request",
-  "scanned_risk",
-  "scs_sbom_drift",
-  "security_exemption",
-  "user"
-]New value: +[
+  "approval_instance",
+  "attestation",
+  "chaos_action",
+  "chaos_action_template",
+  "chaos_experiment",
+  "chaos_experiment_template",
+  "chaos_fault",
+  "chaos_fault_template",
+  "chaos_guard_rule",
+  "chaos_k8s_infrastructure",
+  "chaos_loadtest",
+  "chaos_probe",
+  "chaos_probe_template",
+  "chaos_risk_scan",
+  "chaos_service",
+  "commit",
+  "connector",
+  "cost_anomaly",
+  "cost_budget",
+  "cost_perspective",
+  "cost_perspective_folder",
+  "cost_recommendation",
+  "database_execute_llm_authoring_pipeline",
+  "delegate_token",
+  "environment",
+  "eval_annotation",
+  "eval_dataset",
+  "eval_dataset_item",
+  "eval_git_registration",
+  "eval_metric",
+  "eval_metric_set",
+  "eval_run",
+  "eval_suite",
+  "eval_target",
+  "evaluation",
+  "execution",
+  "file_content",
+  "file_store",
+  "fme_feature_flag",
+  "fme_rule_based_segment_definition",
+  "freeze_window",
+  "gitops_application",
+  "global_freeze",
+  "hql_query",
+  "idp_workflow",
+  "incident",
+  "infrastructure",
+  "online_eval",
+  "pipeline",
+  "pipeline_dynamic_execution",
+  "pipeline_v1",
+  "pr_reviewer",
+  "pull_request",
+  "scanned_risk",
+  "scs_sbom_drift",
+  "security_exemption",
+  "user"
+]
  9. Changed1 schema field changedv3.2.17
    • changedInput schema / properties / resource_type / enum
      Previous value: -[
-  "approval_instance",
-  "chaos_action",
-  "chaos_action_template",
-  "chaos_experiment",
-  "chaos_experiment_template",
-  "chaos_fault",
-  "chaos_fault_template",
-  "chaos_guard_rule",
-  "chaos_k8s_infrastructure",
-  "chaos_loadtest",
-  "chaos_probe",
-  "chaos_probe_template",
-  "commit",
-  "connector",
-  "cost_anomaly",
-  "cost_perspective",
-  "cost_perspective_folder",
-  "cost_recommendation",
-  "database_execute_llm_authoring_pipeline",
-  "delegate_token",
-  "environment",
-  "eval_annotation",
-  "eval_dataset",
-  "eval_dataset_item",
-  "eval_git_registration",
-  "eval_metric",
-  "eval_metric_set",
-  "eval_run",
-  "eval_suite",
-  "eval_target",
-  "evaluation",
-  "execution",
-  "file_content",
-  "file_store",
-  "fme_feature_flag",
-  "fme_rule_based_segment_definition",
-  "freeze_window",
-  "gitops_application",
-  "global_freeze",
-  "hql_query",
-  "idp_workflow",
-  "incident",
-  "infrastructure",
-  "online_eval",
-  "pipeline",
-  "pipeline_dynamic_execution",
-  "pipeline_v1",
-  "pr_reviewer",
-  "pull_request",
-  "scs_sbom_drift",
-  "security_exemption",
-  "user"
-]New value: +[
+  "approval_instance",
+  "chaos_action",
+  "chaos_action_template",
+  "chaos_experiment",
+  "chaos_experiment_template",
+  "chaos_fault",
+  "chaos_fault_template",
+  "chaos_guard_rule",
+  "chaos_k8s_infrastructure",
+  "chaos_loadtest",
+  "chaos_probe",
+  "chaos_probe_template",
+  "chaos_risk_scan",
+  "commit",
+  "connector",
+  "cost_anomaly",
+  "cost_perspective",
+  "cost_perspective_folder",
+  "cost_recommendation",
+  "database_execute_llm_authoring_pipeline",
+  "delegate_token",
+  "environment",
+  "eval_annotation",
+  "eval_dataset",
+  "eval_dataset_item",
+  "eval_git_registration",
+  "eval_metric",
+  "eval_metric_set",
+  "eval_run",
+  "eval_suite",
+  "eval_target",
+  "evaluation",
+  "execution",
+  "file_content",
+  "file_store",
+  "fme_feature_flag",
+  "fme_rule_based_segment_definition",
+  "freeze_window",
+  "gitops_application",
+  "global_freeze",
+  "hql_query",
+  "idp_workflow",
+  "incident",
+  "infrastructure",
+  "online_eval",
+  "pipeline",
+  "pipeline_dynamic_execution",
+  "pipeline_v1",
+  "pr_reviewer",
+  "pull_request",
+  "scanned_risk",
+  "scs_sbom_drift",
+  "security_exemption",
+  "user"
+]
  10. First observedv3.2.10

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare destructive=true, non-idempotent, open-world, so the safety bar is partly met. The description adds real behavioral context: wait=true blocks server-side until terminal status, and timeouts return execution_timed_out=true. It doesn't characterize which specific actions carry medium/high risk (that lives in the confirm param), but the added polling/timeout semantics are substantive.

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?

Front-loaded with the action catalog, then progressively adds wait semantics and the HQL exception. Each sentence carries distinct information, though the HQL sentence is fairly niche and slightly interrupts the otherwise tight flow of general guidance.

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 16-parameter, high-blast-radius action dispatcher with an output schema and rich annotations, the description covers the primary usage patterns and defers action-specific field detail to harness_describe. It lacks guidance on when confirm is required by risk level, but the safety profile and return semantics are otherwise well covered.

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 baseline is 3. The description goes beyond individual property docs by explaining cross-parameter usage: url auto-extracts org/project/type/ID, and queries is only meaningful when paired with resource_type='hql_query' plus action validate/run. These combinations are not obvious from per-property descriptions alone.

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?

Opens with a specific verb+resource ('Execute an action on a Harness resource') and enumerates concrete action families (run/retry/interrupt pipelines, kill/restore FME flags, test connectors, sync GitOps apps, chaos experiments). This clearly positions it against siblings like harness_create or harness_update, which operate on definitions rather than triggering execution.

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

Usage Guidelines4/5

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

Explicit conditions for key modes: 'Pass `wait: true` for pipeline run/retry' to avoid an LLM polling loop, and 'For HQL batch operations pass `queries` with resource_type='hql_query''. It also delegates to harness_describe for per-action params and shows a harness_list call for input set IDs. No explicit statement of when NOT to use it versus harness_create/update, which is the only gap.

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