Skip to main content
Glama
Hardik-Singh

Invariance MCP

Official
by Hardik-Singh
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

cortex_launch

Launch governed Cortex jobs to answer complex operational questions and track divergence/error findings, with ACL-filtered evidence and sync or async execution.

Instructions

Launch a Cortex job through the GOVERNED launcher (POST /v1/cortex/jobs/launch) — the preferred path for the read-only complex_query analyst and divergence_error_tracking. The actor is resolved server-side from the API key and all evidence is ACL-filtered before prompt construction (fails closed against cross-project leak). mode="sync" runs now and embeds result/error; mode="async" enqueues — poll with cortex_get_result or cortex_job_runs. Returns {job_id, status, mode, deduplicated, result?, error?}. Idempotent when idempotency_key is supplied.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modeYes"sync" runs now and embeds the result; "async" enqueues and returns the queued job.
job_kindYescomplex_query = read-only cited analyst for operational questions. divergence_error_tracking = aggregate divergence/error findings for a target.
questionNoFree-form question for the analyst. Recommended for complex_query.
project_idYesProject the job runs against. Used for target access checks and evidence filtering.
target_refYesStable reference to the target (e.g. "run_1", "case_123", or the project_id for target_type="project").
target_typeYesWhat the job runs against.
idempotency_keyNoDedupe key. Re-launching with the same key returns the existing job with deduplicated=true.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.0

TDQS

A4.7/5.0
Behavior5/5

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

Annotations say readOnlyHint=false and destructiveHint=false, but the description adds rich context: server-side actor resolution, ACL filtering before prompt construction, fails-closed behavior against cross-project leak, mode-dependent execution (embed vs enqueue), and idempotency semantics. These go well beyond the annotation flags.

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 a single dense paragraph with no filler. Every clause earns its place: the action, the endpoint, the preferred use cases, the mode behavior, the return shape, and the idempotency note. Information is front-loaded and the key differentiators appear early.

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?

For a 7-parameter tool with no output schema, the description is remarkably complete. It explains the return object, how to poll async jobs, the ACL/security posture, and idempotency. 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.

Parameters3/5

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

Schema description coverage is 100% and the description's parameter mentions (mode sync/async, idempotency_key dedupe, question recommendation) largely mirror the schema text. It adds no new semantics beyond what the schema already conveys, so the baseline 3 is appropriate.

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?

States a specific action (launch a Cortex job) with an endpoint, identifies the governed launcher as the preferred path for specific job kinds (complex_query, divergence_error_tracking), and differentiates from siblings by name. An agent can immediately understand what it does and how it differs from cortex_run_job or cortex_get_job.

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?

Explicitly names the preferred use cases and explains sync vs async modes, pointing to cortex_get_result or cortex_job_runs for polling. It also notes idempotency behavior and the ACL-fails-closed design, giving clear when-to-use guidance without needing to inspect siblings.

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