Skip to main content
Glama

GATA Cafeteras

Brewing guide and recipes

brew_guide
Read-onlyIdempotent

Grind size, coffee-to-water ratio, temperature and time for espresso, moka pot, pour-over, drip, French press and cold brew; recipes (espresso, cortado, cappuccino, latte, café de olla, cold brew); fixes for bitter, burnt, sour or watery coffee; natural vs torrefacto roast and arabica vs robusta; and the official EFSA caffeine figure (no other health claims).

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": {
      "question": "<question>"
    },
    "name": "brew_guide"
  }
}

Input Schema

NameRequiredDescriptionDefault
languageNoLanguage of the answer (default: es). Content is in Spanish; translate it if needed.
questionYesWhat the user wants to make or fix, e.g. «cómo hago un cappuccino», «mi café sale amargo», «molienda para italiana».

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.6/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile needs no restating. The description adds real behavioral constraints beyond them: answers come from a fixed guide, Spanish-first content, and explicitly 'no other health claims' beyond the official EFSA caffeine figure — a scope limit an agent would otherwise not know. It stops short of describing answer length or what happens for out-of-scope questions.

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?

A single dense sentence with zero filler — every clause names a distinct supported topic. However, it reads as a semicolon-separated keyword list with no front-loaded statement of what the tool actually does, so an agent must parse the whole sentence to extract purpose. Efficient but weakly structured.

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

Completeness3/5

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

For a read-only knowledge lookup with a fully documented two-parameter schema and no output schema, the description covers scope, language handling, and a key limitation (no health claims beyond EFSA). It omits what a response looks like (single answer vs. list of recipes), how it behaves for questions outside the listed topics, and any length or citation conventions. Sufficient to select the tool, incomplete for predicting its output.

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%, with both `question` (maxLength 300, with Spanish examples) and `language` (enum es/en, default es) fully documented in the schema, so the baseline of 3 applies. The description adds no extra semantics about how to phrase the question or when to override the language default. It neither compensates nor detracts.

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 enumerates concrete scope: grind size, ratios, temperature/time for six brew methods, a recipe list, off-flavor fixes, roast/species comparisons, and the EFSA caffeine figure. That lets an agent recognize it as the brewing-knowledge tool and distinguishes it from siblings like maintenance_guide or cost_per_cup. It never states the function with a verb (e.g., 'answers brewing questions'), relying on a topic list instead, which keeps it short of a 5.

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?

Usage is only implied by the topic enumeration: an agent can infer it should call this for 'how do I brew X' or 'my coffee tastes bitter' style questions. There is no explicit when-to-use statement, no exclusion of adjacent domains (machine maintenance, capsule compatibility, cost), and no routing to sibling tools. Adequate but leaves the agent to infer boundaries.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources