Skip to main content
Glama

Analyze Nostalgic Dish

analyze_nostalgic_dish
Read-onlyIdempotent

Decomposes a nostalgic dish memory into structured sensory dimensions, then returns a host-model prompt to capture taste, smell, texture, and appearance details for analysis.

Instructions

Provide sensory dimension criteria and a bounded host-model prompt for decomposing a nostalgic dish memory. Returns structured sensory dimension criteria and a promptForAgent for the host model to complete. Use when decomposing a dish into its sensory components. Pass description from the user memory and optionally region.

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": {
      "description": "<description>"
    },
    "name": "analyze_nostalgic_dish"
  }
}

Input Schema

NameRequiredDescriptionDefault
regionNoCultural/geographic region of the dish
descriptionYesThe user's memory/description of the dish

Output Schema

NameRequiredDescriptionDefault
regionYes
descriptionYes
cachedResearchNo
promptForAgentYes
referenceResearchNo
sensoryDimensionsYes
nostalgiaCriticalCriteriaYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.2

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare safe, read-only, idempotent, closed-world behavior, so the bar is lower, and the description still adds genuinely useful behavior: the tool does not perform the decomposition itself but returns criteria plus a 'promptForAgent' for the host model to complete. That division of labor is exactly the kind of trait annotations cannot express. It stops short of describing bounds or limits on the prompt.

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?

Front-loaded with the output artifact and return shape, which is the most decision-relevant information. The final sentence restates the purpose already given in sentence one, a small redundancy, but nothing else is wasted.

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 and full schema description coverage, the description only needs to convey intent, inputs, and the host-model handoff, and it does all three. The main residual gap is workflow placement among the many sibling research/reconstruction tools, which the description never addresses.

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 coverage is 100% with only two well-described parameters, so the schema carries parameter meaning. The description's 'Pass description from the user memory and optionally region' mostly restates the schema's own parameter descriptions without adding format, length, or sourcing nuance beyond them.

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

Purpose4/5

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

The description names a specific verb and output artifact — 'sensory dimension criteria and a bounded host-model prompt' — and states the operation is 'decomposing a nostalgic dish memory'. That is far more concrete than a generic 'analyze' tool, though it does not explicitly contrast itself with nearby siblings like reconstruct_food_memory or generate_minimum_viable_nostalgia.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

'Use when decomposing a dish into its sensory components' gives an implied trigger condition, so an agent knows the rough situation. However, there is no when-not guidance, no ordering relative to the many sibling tools in this workflow, and no stated prerequisite such as whether a resolved dish name should come first.

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