Bryti

Plan the week

plan_week

Destructive

Plan dinners for a week with Bryti's planner, inside the household's rules, events, allergies and pantry. The run is queued and takes one to three minutes; the answer carries a jobId — ask get_planning_status for it. A week that already has planned dinners answers confirmation_required: ask the member, then call again with replace: true. Uses the household's monthly credits, like planning in the app. For the rest of a week that is already planned, use replan_open_days.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "weekStart": "<weekStart>"
    },
    "name": "plan_week"
  }
}

Input Schema

Name	Required	Description
`replace`	No	True when the member has said yes to replacing the dinners already planned this week.
`weekStart`	Yes	Any date in the week to plan; normalized to that week's Monday.
`allowGeneration`	No	How many dinners Bryti may invent this week (0-7). Only when the user says so — «bare to nye retter», «ingen nye retter denne uka». Omit to use the household's own setting.
`allowNearMisses`	No	Whether a day may bend a soft rule or the calendar's guessed busy-evening cap rather than stay without a dinner. Defaults to true; pass false when the user insists every rule holds even if a day ends up empty.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 7, 2026

TDQS

A4.9/5.0

Behavior5/5

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

Goes well beyond the annotations (readOnly=false, destructive=true): it discloses the async queue and 1-3 minute latency, the jobId handle, the confirmation_required refusal mode, and that the run consumes household monthly credits. Those are exactly the non-obvious traits an agent needs before invoking a destructive, non-idempotent, credit-costing 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?

Four sentences, each doing distinct work: purpose, async mechanics, the confirmation branch, cost and the sibling alternative. Purpose and the jobId handoff are front-loaded, and there is no restatement of the tool name or title.

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?

There is no output schema, yet the description still tells the agent what comes back (a jobId, or confirmation_required) and where to poll. For a destructive four-parameter planning tool, nothing needed to call it correctly is missing.

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 coverage is 100%, so the baseline is 3 and the schema already explains weekStart normalization, allowGeneration's 0-7 range and allowNearMisses' soft-rule behavior with good examples. The description adds real meaning on top by tying replace: true to the confirmation_required flow rather than leaving it as a bare boolean.

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+resource ("Plan dinners for a week") and the constraint envelope it operates within (household rules, events, allergies, pantry). It also names the sibling it is not — replan_open_days — for the partially-planned case, so an agent can separate the two without opening schemas.

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?

Explicit routing in both directions: use this to plan a whole week, use replan_open_days for the rest of an already-planned week. It also specifies the escalation path (call, receive confirmation_required, ask the member, call again with replace: true) and the follow-up call (get_planning_status with the jobId).

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

All Bryti tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?