Thread Keeper

Overview Schema Source Related Servers Discussions Admin

agent_status

Read-only

Show autonomous learning loop status including state, backlog, last pass, and RSS. Optionally output structured JSON for menu-bar app integration.

Instructions

Show autonomous learning loops with state, backlog, last pass, and RSS.

Set json_output=True for the same stable shape used by the menu-bar app. Always returns structuredContent (AgentStatusSnapshot); the text block is the JSON dump when json_output else the formatted summary.

Input Schema

Name	Required	Description	Default
`refresh`	No
`json_output`	No

Output Schema

Name	Required	Default
`loops`	No
`agents`	No
`generated_at`	No
`total_rss_kb`	No
`total_rss_mb`	No
`github_budget`	No
`rss_freshness`	No	cached
`running_count`	No
`recent_results`	No
`timed_out_count`	No
`ready_loop_count`	No
`enabled_loop_count`	No
`running_loop_count`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedv0.19.1Oct 15, 2026
- changedInput schema / properties / refresh / default
```
Previous value: -trueNew value: +false
```
- addedOutput schema / properties / rss_freshness
```
Added value: +{
+  "default": "cached",
+  "title": "Rss Freshness",
+  "type": "string"
+}
```

Changed1 schema field changedv0.17.0Aug 28, 2026

addedOutput schema / properties / github_budget

Added value: +{
+  "additionalProperties": true,
+  "title": "Github Budget",
+  "type": "object"
+}

Changed16 schema fields changedv0.14.0Jun 25, 2026

addedOutput schema / additionalProperties
```
Added value: +true
```

addedOutput schema / description

Added value: +"Autonomous learning loops + running children (JSON-ready snapshot)."

addedOutput schema / properties / agents

Added value: +{
+  "items": {
+    "additionalProperties": true,
+    "type": "object"
+  },
+  "title": "Agents",
+  "type": "array"
+}

addedOutput schema / properties / enabled_loop_count

Added value: +{
+  "default": 0,
+  "title": "Enabled Loop Count",
+  "type": "integer"
+}

addedOutput schema / properties / generated_at

Added value: +{
+  "default": 0,
+  "title": "Generated At",
+  "type": "integer"
+}

addedOutput schema / properties / loops

Added value: +{
+  "items": {
+    "additionalProperties": true,
+    "type": "object"
+  },
+  "title": "Loops",
+  "type": "array"
+}

addedOutput schema / properties / ready_loop_count

Added value: +{
+  "default": 0,
+  "title": "Ready Loop Count",
+  "type": "integer"
+}

addedOutput schema / properties / recent_results

Added value: +{
+  "items": {
+    "additionalProperties": true,
+    "type": "object"
+  },
+  "title": "Recent Results",
+  "type": "array"
+}

removedOutput schema / properties / result

Removed value: -{
-  "title": "Result",
-  "type": "string"
-}

addedOutput schema / properties / running_count

Added value: +{
+  "default": 0,
+  "title": "Running Count",
+  "type": "integer"
+}

addedOutput schema / properties / running_loop_count

Added value: +{
+  "default": 0,
+  "title": "Running Loop Count",
+  "type": "integer"
+}

addedOutput schema / properties / timed_out_count

Added value: +{
+  "default": 0,
+  "title": "Timed Out Count",
+  "type": "integer"
+}

addedOutput schema / properties / total_rss_kb

Added value: +{
+  "default": 0,
+  "title": "Total Rss Kb",
+  "type": "integer"
+}

addedOutput schema / properties / total_rss_mb

Added value: +{
+  "default": 0,
+  "title": "Total Rss Mb",
+  "type": "integer"
+}

removedOutput schema / required
```
Removed value: -[
-  "result"
-]
```

changedOutput schema / title

Previous value: -"agent_statusOutput"New value: +"AgentStatusSnapshot"

First observedv0.13.2Jun 17, 2026

TDQS

B3.2/5.0

Behavior3/5

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

readOnlyHint=true already tells the agent this is a safe read. The description adds useful return-shape behavior (always structuredContent, text block varies with json_output), which goes beyond the annotation, but it says nothing about what 'refresh' does or whether it hits the network/backend.

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?

Three short sentences, purpose front-loaded, and no filler. The output-shape sentences are dense but each carries information not in the structured fields.

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?

With an output schema and readOnly annotation, the safety and return-shape burden is largely covered, and the description reinforces the return behavior. The remaining gap is the undefined 'refresh' parameter and no guidance distinguishing this from agent_status_refresh.

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 coverage is 0%, so the description must carry parameter meaning. It fully clarifies json_output (stable menu-bar shape, JSON-text vs formatted-summary output) but leaves 'refresh' completely undefined, so only half the parameters are explained.

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?

States a specific verb ('Show') plus the resource and its scope ('autonomous learning loops with state, backlog, last pass, and RSS'), which concretely describes the payload. However, it never differentiates itself from the near-identically named sibling agent_status_refresh, leaving an agent to guess which one to call.

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

Usage Guidelines2/5

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

It explains how to set json_output but gives no when-to-use conditions and no exclusion against the obvious alternative agent_status_refresh. The presence of that sibling tool makes the missing routing guidance a real gap.

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

Deploy Server