Bernstein - Multi-agent orchestration

bernstein_run

Start an orchestration run to queue multi-agent work for a given goal; returns task_id and run_id for tracking, then check status after the recommended delay to monitor progress.

Instructions

Start an orchestration run. A run does real work and takes minutes to hours; the call returns once the run is queued, not when it finishes. Do not re-issue it while waiting, that starts a second run. Follow the run with bernstein_run_status, passing either the returned task_id or the returned run_id, after waiting the returned poll_after_ms. Pass parent_task_id to create the run as a subtask of an existing task. The queued orchestration writes project state and starts agent work. Host effects: writes files; spawns agent processes; makes network requests.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`goal`	Yes
`role`	No
`scope`	No
`priority`	No
`complexity`	No
`parent_task_id`	No
`estimated_minutes`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
`_meter`	Yes
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

Changed1 schema field changedv3.15.0Aug 14, 2026

changedInput schema / description

Previous value: -"Start an orchestration run. A run does real work and takes minutes to hours; the call returns once the run is queued, not when it finishes. Do not re-issue it while waiting, that starts a second run. Follow the run with bernstein_run_status, passing either the returned task_id or the returned run_id, after waiting the returned poll_after_ms. Pass parent_task_id to create the run as a subtask of an existing task."New value: +"Start an orchestration run. A run does real work and takes minutes to hours; the call returns once the run is queued, not when it finishes. Do not re-issue it while waiting, that starts a second run. Follow the run with bernstein_run_status, passing either the returned task_id or the returned run_id, after waiting the returned poll_after_ms. Pass parent_task_id to create the run as a subtask of an existing task. The queued orchestration writes project state and starts agent work. Host effects: writes files; spawns agent processes; makes network requests."

Changed33 schema fields changedv3.11.0Jul 28, 2026

addedInput schema / $schema

Added value: +"http://json-schema.org/draft-07/schema#"

addedInput schema / additionalProperties
```
Added value: +false
```

addedInput schema / description

Added value: +"Start an orchestration run. A run does real work and takes minutes to hours; the call returns once the run is queued, not when it finishes. Do not re-issue it while waiting, that starts a second run. Follow the run with bernstein_run_status, passing either the returned task_id or the returned run_id, after waiting the returned poll_after_ms. Pass parent_task_id to create the run as a subtask of an existing task."

removedInput schema / properties / complexity / default
```
Removed value: -"medium"
```

addedInput schema / properties / complexity / enum

Added value: +[
+  "low",
+  "medium",
+  "high"
+]

removedInput schema / properties / complexity / title
```
Removed value: -"Complexity"
```
removedInput schema / properties / estimated_minutes / default
```
Removed value: -30
```
addedInput schema / properties / estimated_minutes / maximum
```
Added value: +100000
```
addedInput schema / properties / estimated_minutes / minimum
```
Added value: +0
```
removedInput schema / properties / estimated_minutes / title
```
Removed value: -"Estimated Minutes"
```
addedInput schema / properties / goal / maxLength
```
Added value: +8192
```
addedInput schema / properties / goal / minLength
```
Added value: +1
```
removedInput schema / properties / goal / title
```
Removed value: -"Goal"
```

addedInput schema / properties / parent_task_id

Added value: +{
+  "maxLength": 256,
+  "minLength": 1,
+  "pattern": "^[A-Za-z0-9_.:-]+$",
+  "type": [
+    "string",
+    "null"
+  ]
+}

removedInput schema / properties / priority / default
```
Removed value: -2
```
addedInput schema / properties / priority / maximum
```
Added value: +3
```
addedInput schema / properties / priority / minimum
```
Added value: +1
```
removedInput schema / properties / priority / title
```
Removed value: -"Priority"
```
removedInput schema / properties / role / default
```
Removed value: -"backend"
```
addedInput schema / properties / role / maxLength
```
Added value: +64
```
addedInput schema / properties / role / minLength
```
Added value: +1
```
removedInput schema / properties / role / title
```
Removed value: -"Role"
```
removedInput schema / properties / scope / default
```
Removed value: -"medium"
```

addedInput schema / properties / scope / enum

Added value: +[
+  "small",
+  "medium",
+  "large"
+]

removedInput schema / properties / scope / title
```
Removed value: -"Scope"
```

changedInput schema / title

Previous value: -"bernstein_runArguments"New value: +"bernstein_run"

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

addedOutput schema / properties / _meter

Added value: +{
+  "additionalProperties": false,
+  "properties": {
+    "call_id": {
+      "type": "string"
+    },
+    "cost_usd": {
+      "type": "number"
+    },
+    "error": {
+      "type": "string"
+    },
+    "latency_ms": {
+      "type": "number"
+    },
+    "ok": {
+      "type": "boolean"
+    },
+    "tool": {
+      "type": "string"
+    },
+    "ts": {
+      "type": "string"
+    }
+  },
+  "required": [
+    "tool",
+    "call_id",
+    "latency_ms",
+    "cost_usd",
+    "ok",
+    "ts"
+  ],
+  "type": "object"
+}

addedOutput schema / properties / result / anyOf

Added value: +[
+  {
+    "additionalProperties": false,
+    "properties": {
+      "parent_task_id": {
+        "type": "string"
+      },
+      "poll_after_ms": {
+        "type": "integer"
+      },
+      "run_id": {
+        "type": "string"
+      },
+      "status": {
+        "type": "string"
+      },
+      "task_id": {
+        "type": "string"
+      },
+      "title": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "task_id",
+      "title",
+      "status",
+      "run_id",
+      "poll_after_ms"
+    ],
+    "type": "object"
+  },
+  {
+    "additionalProperties": true,
+    "properties": {
+      "error": {
+        "type": "string"
+      },
+      "hint": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "error"
+    ],
+    "type": "object"
+  }
+]

removedOutput schema / properties / result / title
```
Removed value: -"Result"
```
removedOutput schema / properties / result / type
```
Removed value: -"string"
```

changedOutput schema / required

Previous value: -[
-  "result"
-]New value: +[
+  "result",
+  "_meter"
+]

removedOutput schema / title
```
Removed value: -"bernstein_runOutput"
```

Addedv2.7.0May 25, 2026
Removedv2.6.0May 22, 2026
Addedv2.2.0May 18, 2026
Removedv2.1.0May 18, 2026
Addedv1.10.8May 13, 2026
Removedv1.10.7May 11, 2026
First observedv0.1.0Apr 21, 2026

TDQS

A4.6/5.0

Behavior5/5

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

With no annotations, the description carries the full burden and delivers excellently. It discloses async (returns when queued, not finished), side effects (writes files, spawns agent processes, makes network requests), and the returned poll_after_ms. This is far beyond minimal.

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 dense but every sentence earns its place: purpose, async warning, follow-up, subtask usage, and host effects. It is well-structured and not bloated.

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 complex orchestration tool with side effects, the description covers all critical aspects: queuing model, duplicate-run risk, polling strategy, subtask support, and host-level consequences. Output schema exists, so return values are covered structurally.

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

Parameters2/5

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

Despite 7 parameters and 0% schema description coverage, the description only explains parent_task_id ('pass to create the run as a subtask'). The required 'goal' and others like role, scope, priority, complexity, estimated_minutes are left unexplained, relying solely on naming and enums.

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 opens with 'Start an orchestration run', a specific verb and resource. It clearly distinguishes from siblings like bernstein_run_status (which monitors) and bernstein_cancel by emphasizing the queuing behavior and follow-up steps.

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?

Provides explicit when-to-use and alternatives: tells users not to re-issue while waiting (starts a second run), instructs to follow with bernstein_run_status after waiting poll_after_ms, and mentions parent_task_id for subtasks. This is exemplary usage guidance.

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

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

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/sipyourdrink-ltd/bernstein'

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