Agent Chef

Run Agent Chef

run_agent_chef

Read-only

Start the Agent Chef meal-planning workflow: get the operating manual and due tool calls, execute them in order, then fetch next actions until none remain.

Instructions

The one call to make when the user says 'run agent chef' (or run the app / plan dinner / do the weekly thing). Returns the operating manual plus the checklist of tool calls that are due right now. Execute them in order, then call next_actions again until it returns no actions. Stop before any checkout.

Input Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Output Schema

TableJSON Schema

Name	Required	Description
`week`	No
`phase`	Yes	new_cycle \| voting \| shopping \| cooking \| idle \| subscription_required
`voted`	No
`how_to`	Yes
`actions`	Yes	Ordered checklist of tool calls due now; empty means nothing to do
`billing`	No
`schedule`	Yes
`settings`	No
`on_demand`	No
`hours_open`	No
`next_check`	No
`cycle_start`	No
`instructions`	Yes
`not_yet_voted`	No
`voting_closes_at`	No
`voting_closes_local`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedv0.1.1Oct 3, 2026

addedOutput schema / properties / on_demand

Added value: +{
+  "type": [
+    "string",
+    "null"
+  ]
+}

changedOutput schema / properties / week / anyOf

Previous value: -[
-  {
-    "additionalProperties": true,
-    "properties": {
-      "created_at": {
-        "type": [
-          "string",
-          "null"
-        ]
-      },
-      "id": {
-        "$ref": "#/properties/actions/items/properties/why"
-      },
-      "status": {
-        "enum": [
-          "voting",
-          "selected",
-          "ordered",
-          "done"
-        ],
-        "type": "string"
-      },
-      "voting_closes_at": {
-        "type": [
-          "string",
-          "null"
-        ]
-      },
-      "week_start": {
-        "description": "YYYY-MM-DD",
-        "type": "string"
-      }
-    },
-    "required": [
-      "id",
-      "week_start",
-      "status"
-    ],
-    "type": "object"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "additionalProperties": true,
+    "properties": {
+      "created_at": {
+        "type": [
+          "string",
+          "null"
+        ]
+      },
+      "id": {
+        "$ref": "#/properties/actions/items/properties/why"
+      },
+      "share_url": {
+        "description": "Public page showing this week's winners",
+        "type": [
+          "string",
+          "null"
+        ]
+      },
+      "status": {
+        "enum": [
+          "voting",
+          "selected",
+          "ordered",
+          "done"
+        ],
+        "type": "string"
+      },
+      "voting_closes_at": {
+        "type": [
+          "string",
+          "null"
+        ]
+      },
+      "week_start": {
+        "description": "YYYY-MM-DD",
+        "type": "string"
+      }
+    },
+    "required": [
+      "id",
+      "week_start",
+      "status"
+    ],
+    "type": "object"
+  },
+  {
+    "type": "null"
+  }
+]

First observedv0.1.0Sep 7, 2026

TDQS

A3.7/5.0

Behavior3/5

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

Annotations mark it as read-only, non-destructive, closed-world. The description adds that it returns an operating manual and a checklist, and that you must execute calls in order and stop before checkout—this is valuable operational context. But it doesn't disclose side effects of the orchestrated calls, rate limits, or failure modes.

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?

Three sentences: trigger, return, workflow, stop condition. Every sentence is essential and front-loaded with the trigger.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has no parameters and an output schema, the description provides the necessary usage workflow. It could be more explicit about what the 'operating manual' contains or how to handle errors during execution, but it's largely complete for an orchestration entry point.

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?

There are no parameters, so baseline is 4. The description adds that the return includes an operating manual and checklist, which is extra context, but no parameter details are needed.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description explains the trigger phrases and general workflow, but the tool's actual purpose is somewhat vague. Is it a routine runner? An orchestrator? The name 'run_agent_chef' is clarified only in that it responds to user commands, not what it fundamentally does.

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?

It clearly says when to use: when the user says 'run agent chef' or similar. It describes the workflow: execute returned tool calls, then call next_actions repeatedly until no actions. However, it doesn't compare to sibling tools like next_actions or get_instructions, which might be alternatives in some contexts.

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