cmuxlayer

Overview Schema Source Related Servers Discussions Admin

list_agents

List live agents, filter by state, parent, or blocked prompts, and expand full details to inspect health diagnostics and delivery receipts.

Instructions

List live-derived agents, including registry-persisted prompt blockage and pause state; filter to blocked agents or children with mine/parent_agent_id. Default summary returns flat addressable scalars and hides close tombstones and failed spawns whose surfaces are absent; request a terminal state or detail=full to include them. Full detail also includes provenance, health diagnostics, the registry record, and up to 20 unresolved or attention delivery receipts.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`mine`	No	Return direct children of the calling agent
`repo`	No	Filter by repository
`model`	No	Filter by model
`state`	No	Filter by state
`detail`	No	summary (default): flat addressable scalar rows. full: provenance, health diagnostics, the full registry record, and up to 20 unresolved or attention delivery receipts.	summary
`agent_ids`	No	Return only these agent IDs
`max_age_ms`	No	Maximum acceptable snapshot age in milliseconds (0-5000); topology changes always invalidate the snapshot
`parent_agent_id`	No	Return direct children of this agent
`blocked_on_prompt`	No	Return only agents whose registry records show a live prompt blocker

Output Schema

TableJSON Schema

Name	Required	Description	Default
`ok`	Yes
`count`	No
`agents`	No
`derived_at`	No
`retry_count`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed7 schema fields changedv0.4.88Sep 26, 2026

addedInput schema / properties / agent_ids

Added value: +{
+  "description": "Return only these agent IDs",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

addedInput schema / properties / blocked_on_prompt

Added value: +{
+  "description": "Return only agents whose registry records show a live prompt blocker",
+  "type": "boolean"
+}

addedInput schema / properties / detail

Added value: +{
+  "default": "summary",
+  "description": "summary (default): flat addressable scalar rows. full: provenance, health diagnostics, the full registry record, and up to 20 unresolved or attention delivery receipts.",
+  "enum": [
+    "summary",
+    "full"
+  ],
+  "type": "string"
+}

addedInput schema / properties / max_age_ms

Added value: +{
+  "description": "Maximum acceptable snapshot age in milliseconds (0-5000); topology changes always invalidate the snapshot",
+  "maximum": 5000,
+  "minimum": 0,
+  "type": "integer"
+}

addedInput schema / properties / mine

Added value: +{
+  "default": false,
+  "description": "Return direct children of the calling agent",
+  "type": "boolean"
+}

addedInput schema / properties / parent_agent_id

Added value: +{
+  "description": "Return direct children of this agent",
+  "type": "string"
+}

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": true,
+  "properties": {
+    "agents": {
+      "items": {
+        "additionalProperties": {},
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "count": {
+      "minimum": 0,
+      "type": "integer"
+    },
+    "derived_at": {
+      "type": "number"
+    },
+    "ok": {
+      "type": "boolean"
+    },
+    "retry_count": {
+      "minimum": 0,
+      "type": "integer"
+    }
+  },
+  "required": [
+    "ok",
+    "retry_count"
+  ],
+  "type": "object"
+}

First observedv0.1.0Mar 21, 2026

TDQS

A4.5/5.0

Behavior4/5

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

The description discloses important non-obvious behavior beyond the annotations: default summary hides close tombstones and failed spawns, and full detail adds provenance, health diagnostics, the registry record, and up to 20 receipts. Annotations are all false and provide no safety profile, so this carries most of the burden; side effects and auth are not mentioned, but nothing indicates they are needed for this list operation.

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

Conciseness5/5

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

The description is three dense, front-loaded sentences, each earning its place: what is listed, how filtering works, and what full detail includes. There is no filler or redundant restatement of schema fields.

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 a tool with 9 optional parameters and an output schema, the description covers the non-obvious semantics—live-derived state, hidden tombstones/failed spawns, detail levels, and receipt counts—while the schema covers parameter mechanics. The definition is complete enough for an agent to select and invoke this tool correctly.

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 100%, so the schema already documents every parameter; the description adds value by connecting mine/parent_agent_id to child filtering, blocked_on_prompt to live prompt blockers, and by explaining how state/detail interact with hidden items. This goes beyond simple schema repetition.

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?

Description opens with a specific verb and resource: 'List live-derived agents' and immediately adds distinguishing scope such as registry-persisted prompt blockage, pause state, and child/blocked filtering. This makes it clearly distinct from sibling tools like list_surfaces or spawn_agent.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives clear retrieval guidance: default summary hides tombstones and failed spawns, while requesting a terminal state or detail=full includes them. It does not explicitly name alternative tools or state when not to use this tool, but the context for correct invocation is unambiguous.

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

Deploy Server