Skip to main content
Glama

nucleus

by io.github.eidetic-works

Relay Subscription

nucleus_relay_subscribe
Read-only

Long-poll subscription that pushes ctx.info() on each new inbox file.

Replaces bash polling daemons (watch-relay-*.sh) with server-initiated push. Call once at session start (e.g. via SessionStart hook). Server holds the subscription, watches the calling agent's role-specific inbox dir, and fires info-level notifications on each new relay file arrival. Client re-calls this in a loop for persistent coverage.

Per PR #1 (CCR-inversion-for-relay-pickup): inbox_filter parameter added to BYPASS role-based dir resolution. Use when role detection is unreliable OR when subscribing to a specific canonical inbox (e.g., 'cc_tb'). Closes 3-week-old feedback_relay_arrival_invisible_midsession HARD RULE.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
roleNooverride calling agent's role (default: env-detected from CC_SESSION_ROLE or detect_session_role())
inbox_filterNoexplicit inbox dir NAME (e.g., "cc_tb", "claude_code_main"). When provided, BYPASSES role detection entirely. Recommended for SessionStart hook deterministic arming. Resolves the bug where cc-tb's role detection mapped to wrong inbox.
timeout_secondsNomax subscription duration (60..1800, default 270 = under FastMCP context-cache TTL so re-subscribe doesn't burn cache)

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

TDQS

A4.9/5.0
Behavior5/5

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

Annotations already declare readOnlyHint=true and destructiveHint=false, indicating safety. The description adds significant behavioral details: it's a long-poll, server holds subscription, watches inbox dir, and fires info-level notifications. No contradictions with annotations.

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 well-structured and front-loaded with the core purpose. It includes historical context (PR #1, bug details) that might be slightly verbose but is relevant for understanding. Every sentence contributes meaning, though a minor trim could enhance conciseness.

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?

Given the tool's complexity (long-poll, server-side subscription, looping requirement), the description covers all necessary aspects: functionality, usage instructions, parameter details, and even backstory. An output schema exists, so return values are not needed in the description. It is fully sufficient for an AI agent to use correctly.

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 coverage is 100% with detailed descriptions for all three parameters. The description adds extra context: for inbox_filter, it explains bypassing role detection and recommends it for deterministic arming; for timeout_seconds, it provides reasoning about TTL. This adds value beyond the schema.

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 the tool's core function: 'Long-poll subscription that pushes ctx.info() on each new inbox file.' It differentiates from sibling tools like nucleus_relay by specifying it's a subscription mechanism, and explains the inbox_filter parameter for bypassing role detection, which further distinguishes its use case.

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?

Explicit guidance is provided: 'Call once at session start (e.g. via SessionStart hook).' It also advises using inbox_filter when role detection is unreliable, and mentions the looping requirement for persistent coverage. This gives clear context on when and how to use the tool versus alternatives.

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

All nucleus toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

B3.3/5.0
Disambiguation4/5

Tools are grouped by domain with detailed descriptions, but some overlap exists (e.g., multiple relay-related tools like nucleus_relay, nucleus_relay_subscribe, nucleus_next_message). Overall, most tools have distinct purposes, and descriptions help disambiguate.

Naming Consistency5/5

All tool names follow the 'nucleus_' prefix with a consistent noun-like second part (e.g., nucleus_agents, nucleus_audit, nucleus_delegate). Even compound names like nucleus_lane_feedback maintain the pattern, with no mixing of conventions.

Tool Count3/5

With 28 tools, the count is on the higher end but still justifiable given the broad scope of an agent operating system. The tools cover many necessary functions, though the set could be slightly trimmed for focus.

Completeness4/5

The tool surface covers most aspects of an agent OS: agents, audit, delegation, memory, features, federation, governance, infra, lanes, messaging, orchestration, plans, relay, routing, sessions, slots, sync, tasks, telemetry. Minor gaps like a dedicated config tool are absent but not critical.

Resources