Skip to main content
Glama

configure supervisor task

configure_supervisor_task

Enable opt-in supervision for a monitor job by setting its enabled flag and provider/model policy preferences; this requires a write-scope key and does not start agent connections or paid API calls.

Instructions

Enable opt-in supervision. Provider/model are external-agent preferences; this does not connect an agent or start paid API calls. Requires a write-scope key.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "jobId": "<jobId>",
      "enabled": "<enabled>",
      "policy": "<policy>"
    },
    "name": "configure_supervisor_task"
  }
}

Input Schema

NameRequiredDescriptionDefault
jobIdYes
policyYes
enabledYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.5.0

TDQS

C2.9/5.0
Behavior3/5

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

With no annotations, the description carries the full burden, and it does add real value: the write-scope key requirement and the explicit statement that no agent connection or paid calls occur. It omits what a mutation of an already-enabled task does, whether existing policy fields are overwritten or defaulted, and whether the call is idempotent.

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?

Three short, front-loaded sentences with no filler; the safety caveat precedes the auth requirement. The provider/model sentence is the least central but still carries a non-obvious semantic point.

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?

A mutation tool with a nested policy object, zero annotation coverage, no output schema and 0% schema description coverage needs substantially more than three sentences. An agent can learn it is safe and needs a write key, but not what the call actually changes.

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

Parameters2/5

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

Schema description coverage is 0% and the nested policy object hides seven subfields with defaults. The description only speaks to provider/model (framing them as inert external-agent preferences), leaving jobId, enabled, allowActions, maxAttempts, allowWait, allowDeviceSessions and approvedProxies with no meaning anywhere.

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?

"Enable opt-in supervision" gives a verb and a concept but never says what is actually configured: no mention of attaching a policy to a jobId, of the enabled flag, or of the policy contents. It is distinguishable from start/apply siblings only by inference from the negative clause about not connecting an agent.

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

Usage Guidelines3/5

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

There is an implicit when-to-use signal in the exclusions ("does not connect an agent or start paid API calls"), which suggests this is the cheap setup step ahead of apply/start. No alternative is named (preview_supervisor_task, test_supervisor_task, apply_supervisor_task) and no precondition beyond the key scope is stated.

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