Skip to main content
Glama

nucleus_telemetry

Configure LLM model tiers, record interaction telemetry for training signals, track costs, and manage safety controls like kill switches and notification pausing.

Instructions

Configure LLM model tiers, record interaction telemetry for training signal generation, track costs, and manage safety controls including kill switches and notification pausing. Use this tool when you need to set which AI models are used for different task types, log usage data, check cost dashboards, or control emergency stops. Do NOT use for persistent memory (use nucleus_engrams), task management (use nucleus_tasks), or agent lifecycle (use nucleus_agents). Actions: 'set_llm_tier' configures which model (opus/sonnet/haiku) to use for specific task contexts. 'get_llm_status' returns current tier configuration. 'record_interaction' logs a tool invocation with token counts and latency for training signal generation (side effect: appends to telemetry log). 'value_ratio' calculates cost-effectiveness metrics across recent interactions. 'check_kill_switch' queries whether all operations should halt — returns boolean. 'pause_notifications' temporarily stops PEFS alert delivery. 'resume_notifications' re-enables alerts. 'record_feedback' captures human ratings (1-5 scale) on AI outputs for DPO training pairs. 'mark_high_impact' flags an interaction for human review. 'agent_cost_dashboard' shows per-agent token spending and cost breakdown. 'request_handoff' initiates a work transfer between agents. 'dispatch_metrics' shows tool dispatch statistics. Prerequisites: .brain directory. Kill switch state persists in .brain/governance/kill_switch.json. Returns JSON with {success: boolean, data: object}. Example: {action: 'record_feedback', params: {interaction_id: 'int_abc', rating: 5, comment: 'Perfect fix'}} returns {success: true, data: {recorded: true, dpo_pair_created: true}}.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
actionYesSelect the telemetry or safety control action. 'get_llm_status'/'value_ratio'/'check_kill_switch'/'agent_cost_dashboard'/'dispatch_metrics'/'check_protocol'/'get_handoffs' are read-only queries. 'set_llm_tier' changes model configuration. 'record_interaction'/'record_feedback'/'mark_high_impact' write telemetry data to disk. 'pause_notifications'/'resume_notifications' toggle PEFS alert delivery. 'request_handoff' initiates agent-to-agent work transfer.
paramsNoAction-specific parameters as key-value pairs. set_llm_tier: {tier: string (required, 'opus'|'sonnet'|'haiku'), context: string (optional, task type this tier applies to, e.g. 'code_review')}. record_interaction: {tool_name: string (required), tokens_in: integer (required), tokens_out: integer (required), latency_ms: integer (required)}. record_feedback: {interaction_id: string (required), rating: integer (required, 1 to 5 scale), comment: string (optional)}. mark_high_impact: {interaction_id: string (required), reason: string (required, why this is high-impact)}. request_handoff: {from_agent: string (required), to_agent: string (required), context: object (required, handoff payload with task info)}. get_llm_status/value_ratio/check_kill_switch/pause_notifications/resume_notifications/check_protocol/get_handoffs/agent_cost_dashboard/dispatch_metrics: no parameters needed.
Behavior5/5

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

Discloses behavioral traits beyond annotations: notes side-effects (record_interaction appends to telemetry log), persistence (kill switch state in .brain/governance/kill_switch.json), and categorizes actions as read-only vs write. No contradiction with annotations (readOnlyHint=false is consistent with mixed operations).

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?

The description is long but well-structured: starts with a summary, then usage guidance, then action-by-action details. Every sentence adds value. Minor deduction for length; could be slightly more concise without losing information.

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?

Completely covers the tool's complexity: 14 actions, nested params, no output schema. Provides prerequisites (.brain directory), file path for kill switch, return format, and an example. No missing information needed for correct invocation.

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

Parameters5/5

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

Schema already covers 100% of parameters with descriptions, but the description adds further details: example values for enums (opus/sonnet/haiku), clarifies which actions need parameters, and provides an example with return shape. This goes beyond the schema's minimal description.

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?

The description clearly states it configures LLM tiers, records telemetry, tracks costs, and manages safety controls. It lists specific actions grouped by purpose and explicitly differentiates from sibling tools by stating what it is NOT for (nucleus_engrams, nucleus_tasks, nucleus_agents).

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 provides use contexts ('when you need to set which AI models...') and lists alternatives for other tasks. The description gives clear when-to-use and when-not-to-use guidance with named sibling tools.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/eidetic-works/nucleus-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server