Skip to main content
Glama

get_taste_interview

Read-onlyIdempotent

Runs a design taste interview for a new project: asks core questions about identity, aesthetic, voice, and references, then builds a profile. Use refine mode to update after rejection.

Instructions

START HERE on a NEW project: returns a deterministic calibration interview. By default (depth:'first_run') it is COMPRESSED to just 5 core questions — identity, genesis (what already exists for the project — a brand, a design system, brand assets — routing whatever is missing to generation: mood board approval stop, then generate_design_system save:true, then init_design_md), aesthetic, voice, matchers — so a first-time kickoff is fast; every other question (references, the remaining ten design dimensions, any learned dimensions, rule exceptions, and the open-ended special question) is still returned under more_questions for the agent to offer as optional deeper calibration. Pass depth:'full' to get everything at once as a single flat questions list (the eleven design dimensions — typography, spacing, color, layout, motion, imagery, entrance, loading, navigation, aesthetic, libraries — each grounded in what the profile already enforces and most carrying multiple-choice options; the libraries question names specialty tech in plain outcome language and states the default build target for sites: a Next.js app, unless the user prefers otherwise). The voice question always renders the same message in three registers (formal-technical / warm-conversational / punchy-editorial) so the user picks by ear, not by adjective — asked even when the profile has zero voice rules. Every question carries skippable + priority ('core'|'extended'); only identity is required. A 'references' question (offered in more_questions on first_run) invites example URLs/screenshots/files, each interviewed with follow-ups about what specifically draws the person, folded into the matching design_notes. The full interview closes with an open-ended 'special' question (any texture, signature detail, motif, or easter egg nothing else asked about); once the person has other bound surfaces, it carries suggestions — the special touches they chose elsewhere. Ask the user the returned questions conversationally, then persist the answers with bind_taste_surface (dimension answers go in design_notes). Run this BEFORE the first audit_taste on any project that has no binding yet — audit results include a calibration_hint when calibration is missing. When a user dislikes generated/designed output on an ALREADY-calibrated project, re-run with mode:'refine' instead of starting over — dissatisfaction is a calibration signal, not a dead end: it requires an existing binding, then interviews what specifically fell short, offers to keep/tighten/replace each stored design_notes value, re-asks voice, and offers to log a reject precedent via label_finding. mode defaults to 'kickoff'.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modeNo'kickoff' (default) calibrates a project with no binding yet. 'refine' re-interviews an ALREADY-bound project after the user rejects generated/designed output — requires an existing binding (throws naming get_taste_interview kickoff otherwise) and asks what fell short, then per-dimension keep/tighten/replace, then voice, then an optional reject precedent.
depthNo'first_run' (default) returns only the 5 core questions (identity, genesis, aesthetic, voice, matchers) plus a `more_questions` array with everything else for optional deeper calibration. 'full' returns every question flattened into `questions`, as before.
profileYesTaste profile name (see list_taste_profiles).
projectNoProject identifier the binding will be saved under, e.g. 'raven-mcp' or 'portfolio'. Include it so the interview can show any existing binding.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv2.5.1
    • changedInput schema / properties / depth / description
      Previous value: -"'first_run' (default) returns only the 4 core questions (identity, aesthetic, voice, matchers) plus a `more_questions` array with everything else for optional deeper calibration. 'full' returns every question flattened into `questions`, as before."New value: +"'first_run' (default) returns only the 5 core questions (identity, genesis, aesthetic, voice, matchers) plus a `more_questions` array with everything else for optional deeper calibration. 'full' returns every question flattened into `questions`, as before."
  2. First observedv2.2.9

TDQS

A4.3/5.0
Behavior4/5

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

Goes well beyond the annotations by disclosing determinism, the depth-dependent output shape (5 core questions + more_questions vs a flat full list), per-question flags, the voice question's three registers, and an error condition ('throws naming get_taste_interview kickoff otherwise'). Despite that, the phrase 'throws naming get_taste_interview kickoff otherwise' is garbled and slightly obscures the exact error behavior; otherwise this is notably transparent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single massive block of text with deep parentheticals and run-on sentences, including a garbled clause ('throws naming get_taste_interview kickoff otherwise') that hinders skimming. While front-loaded with the 'START HERE' instruction, the lack of line breaks or focused headings makes even a slightly complex tool much harder to parse than it needs to be.

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?

Despite having no output schema, the description covers the core return shapes (questions, more_questions, flat question list), the question structure (skippable, priority, required only for identity), the integration point with audit_taste, and the post-interview persistence step. Some edge cases like presentation of more_questions and exact error handling are only hinted at, but nothing is fundamentally 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 description coverage is 100%, so the baseline is 3; the description meaningfully adds semantics by clarifying why the project parameter matters ('Include it so the interview can show any existing binding'), explaining mode:'refine' behavior (involves keep/tighten/replace), and detailing depth effect on the returned question shape. Not all parameters get equivalent depth, but the added value pushes it above baseline.

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?

The opening sentence says exactly what the tool does with a specific verb and resource: 'returns a deterministic calibration interview.' It immediately establishes the new-project scope ('START HERE on a NEW project') and the refine-already-calibrated alternative, differentiating itself from the sibling tools it pairs with (bind_taste_surface for persistence, audit_taste for later audits).

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?

The description is explicit about when to use it: 'Run this BEFORE the first audit_taste on any project that has no binding yet', 'START HERE on a NEW project', and use mode:'refine' instead of starting over when an already-calibrated user dislikes output. It also prescribes the follow-up action (persist with bind_taste_surface), leaving no ambiguity about the workflow.

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

Install Server

Other Tools