Skip to main content
Glama

Prometheor settings

settings
DestructiveIdempotent

Reads and changes the owner's Prometheor settings by the owner's words, like the account page: the language, what each connected AI may do and how it hands work on, apps on the owner's computers, computer and project names, who builds in a project, the limit takeover and Prometheor as a whole. Call it only when the owner asks to see or change a setting (for example "Codex should only watch", "call my Mac Studio", "switch Prometheor off", "set Prometheor to German"). action read (default) lists the settings and what each takes; action set changes one. ai: the AI's name as the owner says it, or "me" for yourself. Lowering a right or switching something off happens at once. Widening what an AI may do, switching something on again, removing an AI or a computer, and switching the limit takeover off never happen by prompt: the answer then has confirm_link, which you give the owner (only their tap confirms). Payment, plan, account data, pairing a computer and wake keys stay on the account page (account_page). Settings: language, ai_access, ai_mode, ai_chat_read, ai_remove, app, computer_name, computer_remove, project_name, project_builder, project_archive, limit_takeover, orchestration, plan, account_data, connect_computer, wake_key, sign_out.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "settings"
  }
}

Input Schema

NameRequiredDescriptionDefault
aiNoFor ai_* settings: the AI's name as the owner says it (e.g. "Codex", "Grok Bot"), or "me" for yourself.
appNoFor app, ai_mode duo and project_builder: the app on the owner's computer.
nameNoFor computer_name and project_name: the new name.
valueNoThe new value: on/off, a language code (en, de, es, fr, it, pt, ja, system), tasks/watch/off for ai_access, ask/auto/duo for ai_mode.
actionNoread (default) or set.read
folderNoFor project_* settings: the project's folder or name.
settingNoWith set: the setting to change; action read shows what each takes.
computerNoFor app and computer_* settings when the owner has more than one computer: its name.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.8/5.0
Behavior5/5

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

Goes well beyond the annotations by splitting operations into immediate versus gated: lowering rights or switching off applies at once, while widening access, re-enabling, removing an AI/computer, and disabling the limit takeover never apply from a prompt and instead return a confirm_link that only the owner's tap can confirm. That is exactly the destructive/irreversible detail destructiveHint=true alone cannot convey.

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 purpose, then usage gate, then the confirmation model, then scope exclusions — a sensible priority order. The final sentence re-lists all eighteen setting identifiers already present as schema enum values, which is wasted length and creates mild tension with the sentence saying plan/account_data/connect_computer/wake_key belong on the account page.

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 an 8-parameter destructive mutation tool with no output schema, the description covers the trigger, the read/set branching, the per-setting semantics, the confirmation handshake, and the redirect for out-of-scope settings. Nothing an agent needs in order to call it or to handle the confirm_link response is missing.

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 the baseline is 3, but the description adds real meaning the bare enum identifiers lack — it glosses what each setting actually controls ('what each connected AI may do and how it hands work on', 'who builds in a project', 'the limit takeover'). It also restates the ai/action semantics, which is duplicative rather than additive.

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 verb pair and resource ('Reads and changes the owner's Prometheor settings') and immediately enumerates the setting domains it covers (language, AI permissions, apps, computer/project names, limit takeover). It also names the sibling it is not ('account_page') for the account-related settings, so an agent can separate the two without opening a schema.

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?

Gives an explicit trigger condition ('Call it only when the owner asks to see or change a setting') with four concrete owner-phrase examples, plus explicit exclusions routed elsewhere (payment, plan, account data, pairing, wake keys go to account_page). It also states the read-vs-set selection rule ('action read (default) lists... action set changes one').

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources