LUT Lunch MCP

Menu history statistics

menu_stats

Read-onlyIdempotent

Analyze recorded lunch history to see how often a dish or diet was served, when it first and last appeared, and which dishes are most common by restaurant, month, or weekday.

Instructions

Statistics from the recorded lunch history of LUT Skinnarila campus restaurants: how often dishes matching a word or diet were served, when they were first and last served, counts per restaurant, month or weekday, and the most common dishes. Use it for questions like "how often is salmon served?", "when did Yolo last have salmon soup?", "what's the most common soup?" or "has there been more vegan food lately?". Searches Finnish and English dish names (try the Finnish word, e.g. "lohi", if English finds nothing). History only covers days since collection started; the result says which period it covers.

Input Schema

Name	Required	Description	Default
`to`	No	Last day to include. Default: today.
`top`	No	How many of the most common matching dishes to list (0–20). Default: 10.
`diet`	No	Only dishes labelled with every one of these diets.
`from`	No	First day to include. Default: first recorded day.
`query`	No	Word or part of a dish name, in English or Finnish (e.g. "salmon" or "lohi").
`group_by`	No	How to split the counts. Default: restaurant.	restaurant
`language`	No	Language for dish and course names. Default: en.	en
`restaurants`	No	Restaurant ids to include. Default: all.

Output Schema

Name	Required	Description	Default
`today`	Yes
`groups`	Yes
`notice`	Yes
`history`	Yes
`matches`	Yes
`searched`	Yes
`timezone`	Yes
`top_dishes`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Addedv0.2.0Oct 24, 2026

TDQS

A3.9/5.0

Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint, so safety and repeatability are covered. The description contributes real extra context—the finite history window and the fact that the result self-reports the covered period—but says nothing about result size limits (top capped at 20) or performance characteristics.

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?

Two sentences, both dense with signal: capabilities and return contents first, usage examples and the search-language fallback second. Slightly long single sentences, but no filler and the most important information leads.

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?

With an output schema present, the description needn't document return values, and it correctly focuses on scope (the finite history window), search semantics, and representative use cases. The only omission is any hint about how filters combine or the meaning of group_by behavior under aggregation.

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 description coverage is 100%, including enum values and defaults, so the schema carries parameter meaning on its own. The description reinforces the language dimension of 'query' (Finnish vs English matching) but adds no syntax or format guidance beyond what the schema already states.

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 resource (aggregate statistics over recorded lunch history) and enumerates exactly what it computes: frequency of matches, first/last served dates, counts grouped by restaurant/month/weekday, and top dishes. A concrete example set ('how often is salmon served?') makes the capability unmistakable and separates it from sibling tools like get_menu or find_dishes.

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?

Gives four concrete question patterns that select this tool, plus a practical search tip (try the Finnish word if English finds nothing) and the caveat that history only spans days since collection started. It never explicitly names a sibling tool as the alternative for adjacent questions, which keeps it below a 5.

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

Deploy Server