Skip to main content
Glama

test supervisor task

test_supervisor_task

Runs a candidate browser preview without an LLM to verify task goals via expected text, inspect current targets, and apply unique click or timed wait edits.

Instructions

Run a candidate browser preview without an LLM. expectedText must reflect the task goal. An empty patch can inspect current targets. CLICK locators must be unique; WAIT uses seconds. Standard tasks use actionEdits, Intelligence uses sourceId + cachedActions. Preview/browser infrastructure costs follow existing rules. 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>",
      "leaseToken": "<leaseToken>",
      "repair": "<repair>"
    },
    "name": "test_supervisor_task"
  }
}

Input Schema

NameRequiredDescriptionDefault
jobIdYes
repairYes
leaseTokenYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.5.0

TDQS

A3.5/5.0
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 does disclose meaningful traits: no LLM is involved, a write-scope key is required, preview/browser infrastructure costs apply, and CLICK locators must be unique. It stops short of saying whether the run mutates anything server-side or what a failed preview returns, which matters for a write-scope-gated tool.

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?

Six short sentences, front-loaded with the core action, and no filler. The telegraphic, fragment-heavy style ('CLICK locators must be unique; WAIT uses seconds') is efficient but costs some readability for an unfamiliar agent.

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

Completeness3/5

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

For a tool with a deeply nested 3-parameter schema at 0% description coverage, no annotations, and no output schema, the description covers the domain semantics well but omits the identity/lease parameters and says nothing about outcomes or failure modes. An agent could form a valid call only by guessing at several fields.

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 description coverage is 0%, so the description has to compensate, and it does for the important parts: expectedText must reflect the task goal, actionEdits vs sourceId + cachedActions map to task modes, WAIT values are in seconds, and empty patches are legal. It leaves jobId, leaseToken, proxy, deviceId, expectPdf, waitUntil, waitSeconds, and cacheAiSetup entirely unexplained, so coverage is partial.

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?

The first sentence gives a specific verb and resource — run a candidate browser preview without an LLM — which distinguishes it from the LLM-driven preview/apply siblings. It never names an alternative explicitly, but the 'without an LLM' qualifier is a real functional differentiator an agent can act on.

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?

It offers conditional usage cues: an empty patch inspects current targets, standard tasks use actionEdits, Intelligence tasks use sourceId + cachedActions. However, it never states when to choose this over preview_supervisor_task or apply_supervisor_task, so the guidance is implied rather than comparative.

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