Skip to main content
Glama
bzdOS

hubd

by bzdOS
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

hub_presence

Report which agents are heartbeating across mesh nodes, including per-node observations and coverage gaps, so unseen roles are not mistaken for dead workers.

Instructions

The fleet roster as far as it can honestly be seen from here: this node's live registry plus every other node's published snapshot (presence..json, one small file per node, refreshed on heartbeat). Each row carries observedOn — WHICH node saw that heartbeat — and alsoOn when one agent name turns up on several. Read coverage before believing any absence: it lists every current mesh member with the age of its snapshot, or null when it has published none, and blindTo/note say so outright. That distinction is the reason this tool exists in this shape — one role read as 383 minutes since heartbeat on one node and 5.9 days on another, nothing was stale and nothing had diverged, the registries were simply of different machines, and an orchestrator escalated "worker is dead" four times over 92 hours while the worker worked. A role nobody reports is invisible, which is NOT the same as dead.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
cwdNoonly agents whose heartbeat cwd is this directory or under it — "who is in this checkout"
fullNoreturn everything, uncapped. By default long lists are trimmed to fit an agent context and what was left out is reported in `truncated`.
roleNofilter to agents heartbeating under this role
projectNoonly agents whose heartbeat cwd resolves to this project (marker, sync path or folder name)
aliveOnlyNodrop stale (TTL-expired) records, default false
memberDaysNoa node counts as a mesh member if it wrote within N days, default 30 — retired node names drop out of `coverage` on their own

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.9.15
    • addedInput schema / properties / cwd
      Added value: +{
+  "description": "only agents whose heartbeat cwd is this directory or under it — \"who is in this checkout\"",
+  "type": "string"
+}
    • addedInput schema / properties / project
      Added value: +{
+  "description": "only agents whose heartbeat cwd resolves to this project (marker, sync path or folder name)",
+  "type": "string"
+}
  2. Changed1 schema field changedv0.9.14
    • addedInput schema / properties / memberDays
      Added value: +{
+  "description": "a node counts as a mesh member if it wrote within N days, default 30 — retired node names drop out of `coverage` on their own",
+  "type": "integer"
+}
  3. Changed1 schema field changedv0.9.0
    • addedInput schema / properties / full
      Added value: +{
+  "description": "return everything, uncapped. By default long lists are trimmed to fit an agent context and what was left out is reported in `truncated`.",
+  "type": "boolean"
+}
  4. Addedv0.5.0

TDQS

B3.4/5.0
Behavior4/5

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

No annotations exist, so the description carries the full burden, and it does significant work: it discloses snapshot freshness via heartbeat, the observedOn/alsoOn/coverage/blindTo fields, and the 'invisible ≠ dead' semantic that governs interpretation. It doesn't cover refresh cadence precisely or describe auth/rate behavior, but the behavioral interpretation guidance is strong and specific.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long and discursively structured: the core capability is buried in a marquee paragraph, followed by an extended war story about a worker dead for 92 hours. That anecdote earns its place as motivation but is disproportionately dominant; the front-loaded 'fleet roster' line is good, yet overall the prose is more essay than field.

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 read-only roster query with 100% schema coverage and no output schema, the description covers the interpretation-critical parts (coverage/blindTo/observedOn) that structured fields alone wouldn't convey. However, it's weak on concrete usage guidance and doesn't explain the return shape despite having no output schema, leaving some gaps an agent would want filled.

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

Parameters3/5

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

Schema description coverage is already 100%, with each of the six parameters documented (cwd, full, role, project, aliveOnly, memberDays). The description adds contextual color about coverage and truncation but does not add format or interaction detail beyond what the schema already provides, so baseline 3 applies.

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 description states a specific resource ('the fleet roster') and scope ('this node's live registry plus every other node's published snapshot'), and the fields it exposes (observedOn, alsoOn, coverage) make the intent clear. It doesn't name a specific sibling to differentiate from, but the roster/presence framing is distinct enough to be actionable.

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?

The description implies when to use it — checking presence before believing an absence, reading coverage/blindTo before concluding a node is dead — but there's no explicit when/when-not or sibling alternative named. The vivid anti-pattern example (escalating a worker as dead four times) conveys the intended context indirectly rather than stating a rule.

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

Deploy Server

Other Tools