Skip to main content
Glama
talvola

bar-assistant-mcp

by talvola

bar_audit_ingredients

Audit bottles for missing image, ABV, or flavor data to clean up incomplete historical records. Optionally filter by category or shelf status.

Instructions

Audit real bottles for incomplete data, so historical gaps can be cleaned up.

This is the canonical "what's incomplete" worklist — it reports real bottles, not commodity leaves. (For raw structural listing use bar_list_ingredients.)

Reports, per specific bottle (leaf ingredient — generic parent categories are skipped), which of these are missing:

  • image — commodity leaves (juices, syrups, produce, dairy, ice) are excluded by default, so this is "bottles needing artwork".

  • ABV / strength (only for bottles in a tracked spirit/liqueur category)

  • flavor profile — only for bottles whose category supports flavor axes (gin, rye, bourbon, scotch, american_single_malt, aquavit, amaro, herbal_liqueur, rum, vermouth, fruit_liqueur). Bottles in categories with no axes are never flagged for a missing profile.

Axis support is seeded from a known map AND learned live from bottles that already have a profile, so it stays correct as the taxonomy grows.

Args:

  • category: restrict to one category's subtree (pass the category ingredient's ID, e.g. 347 Rye). Strongly recommended — it makes the flavor scan far cheaper.

  • on_shelf_only: only audit bottles currently in the bar.

  • check_flavor: set False to skip the per-bottle flavor-profile scan (faster; reports only image/ABV gaps).

  • include_uncategorized: also audit root-level leaves not filed under any category. Off by default.

  • include_commodities: include commodity items (juices, syrups, produce…) in the missing-image list. Off by default.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
categoryNo
check_flavorNo
on_shelf_onlyNo
include_commoditiesNo
include_uncategorizedNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.7/5.0
Behavior4/5

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

With no annotations, the description carries the burden and does well: it discloses default exclusions (commodities, uncategorized), the flavor-axis seeding/learning behavior, and per-category applicability rules. It stops short of stating permissions, cost profile in general, or output shape, though an output schema exists to cover returns.

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 summary sentence, then bullets and an args block that are easy to scan. Slightly verbose and repetitive — the commodity-leaves exclusion is explained twice (once in the purpose and again under image) — but nothing is off-topic.

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?

For a 5-param, zero-required audit tool with an output schema, the description covers purpose, scoping, defaults, per-flag effects, and category-specific semantics. An agent has everything needed to invoke it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate, and it does — all five parameters are explained with rationale and defaults (category as subtree ID with example, check_flavor's speed tradeoff, on_shelf_only, include_uncategorized, include_commodities).

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 ('audit real bottles for incomplete data') and immediately distinguishes itself from the nearest alternative by naming bar_list_ingredients as the raw structural listing. It also defines scope ('real bottles, not commodity leaves'), so an agent can tell it apart from siblings without opening a schema.

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 routes to bar_list_ingredients for raw listing, states the canonical role as the 'what's incomplete' worklist, and even recommends passing category because it 'makes the flavor scan far cheaper'. Defaults and opt-in flags (include_uncategorized, include_commodities) are stated with their conditions.

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