Agent Chef

What should happen now

next_actions

Read-only

Returns your current Agent Chef phase and an ordered checklist of due meal-planning actions: propose dinners, send ballots, lock picks, build grocery lists. Run them, then repeat until empty.

Instructions

START HERE. Returns the current phase and an ordered checklist of tool calls that are due right now (propose, send ballot, remind non-voters, add options for feedback, lock in, shop), with why and the arguments/message text to use. Execute them, then call again until empty. Idempotent and time-aware; safe to call on a schedule.

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
`actions`	Yes	Ordered checklist of tool calls due now; empty means nothing to do
`billing`	No
`settings`	No
`on_demand`	No
`hours_open`	No
`next_check`	No
`cycle_start`	No
`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

A4.9/5.0

Behavior5/5

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

Annotations already confirm read-only/no destruction/no open world. The description adds behavior beyond them: idempotency, time-awareness, safe scheduled use, an iterative call-until-empty loop, and that it returns why plus arguments/message text. These are non-obvious traits an agent needs.

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?

Front-loaded with START HERE, then three tight sentences with no filler. Every sentence carries actionable information about return content, execution loop, and safe scheduling.

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?

An output schema exists, so return format details need not be repeated. The description covers purpose, usage loop, idempotency, and safety for a zero-parameter orchestrator with rich annotations, leaving no critical gap for correct invocation.

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?

Zero parameters means the baseline is 4 per the rules. There are no schema fields to misinterpret, and the description correctly avoids inventing parameter semantics.

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?

States a specific verb (returns) and resource (current phase and ordered checklist of tool calls due now), and distinguishes itself as the orchestrator entry point by listing the phases it covers (propose, send ballot, remind non-voters, add options, lock in, shop). This clearly separates it from the individual action siblings.

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?

Explicitly says START HERE and instructs to execute the returned calls then call again until empty. It also declares the tool idempotent and time-aware, safe to call on a schedule. This fully specifies when and how to use it as the entry point.

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