Skip to main content
Glama

bind_taste_surface

Destructive

Persist a project's taste profile calibration by binding interview answers to a surface, enabling automatic rule severity adjustment in audits.

Instructions

Persist a project's surface calibration for a taste profile — the answers from get_taste_interview. A binding records: the surface string scoped rules match against (e.g. 'product-site'), URL hosts that identify the project in url-mode audits, per-rule severity overrides (block|warn|nit|off — 'off' silences a rule on this surface), an optional voice/tone note, per-dimension design_notes (typography, spacing, color, layout, motion, imagery, entrance, loading, navigation, aesthetic, libraries, special — the interview's design:* answers), and a first-class references array — the example sites the person pointed to. References are NOT lossy prose: each url is captured live and its PageTraits (scheme, luminance, animation/scroll motion, text density) are stored on the binding, then design_notes are consistency-checked against what the references ACTUALLY are. A 'dark, cinematic' color note against two references that both render light comes back as a consistency_warning to surface to the user. Upserts by project name (~/.raven/taste/.surfaces.json); on a re-bind, omitted references/design_notes/voice_note/overrides/hosts carry forward and are reported in carried_forward, while explicit empty values clear them. When the design_notes name an expensive technique (three.js/WebGL, GSAP scroll choreography, anime.js staggered motion, glassmorphism, a branded loader, lottie, kinetic display type…), the result carries build_hints — a concrete recipe + canonical public example sources per technique, so the builder sees the HOW at kickoff, BEFORE building; an expensive note is not license to drop it. After binding, audit_taste with project:'' or a bound url applies the calibration automatically: matching scoped rules run at full severity, non-matching ones are skipped, overrides re-tune the rest. ENFORCED: a bind whose RESULT has no calibration content (no design_notes/voice_note/references/overrides) is REFUSED — a brand-new surface bound bare (the fingerprint of a skipped kickoff interview) and a re-bind that explicitly clears every calibration field alike; a stored uncalibrated_ack carries forward on re-binds, so only a NEW clear-everything requires a fresh ack. Run get_taste_interview, ask the USER, and bind their answers; the uncalibrated_ack escape hatch exists only for a user who was interviewed and deliberately skipped every dimension.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
hostsNoURL hostnames that identify this project (e.g. ravenmcp.ai) — matched in url-mode audits, subdomains included.
profileYesTaste profile name.
projectYesProject identifier, e.g. 'raven-mcp', 'portfolio'.
surfaceYesWhat this surface IS, in scope-matchable words: 'monochrome portfolio', 'product-site', 'developer docs'. Scoped rules activate when their scope tokens overlap this string.
overridesNoPer-rule re-tuning for this surface (e.g. relax a voice rule to nit on a product site).
referencesNoFirst-class reference examples the person pointed to. Each url is captured live (traits stored on the binding), and design_notes are consistency-checked against them — contradictions come back as consistency_warnings.
voice_noteNoShort tone guidance for this surface (e.g. 'Product register: benefits may be stated plainly; still no hype verbs'). Echoed as voice_note in audit results.
design_notesNoPer-dimension design preferences from the interview's design:* questions — keys are short dimension names (typography, spacing, color, layout, motion, imagery, entrance, loading, navigation, aesthetic, libraries, special; trimmed + lowercased, must match ^[a-z][a-z0-9_-]{0,31}$ after normalization, no two keys may collide), values are the user's non-empty answers. Echoed as design_notes in every audit so generation is shaped by them, and treated as ACCEPTANCE CRITERIA a build must visibly satisfy.
uncalibrated_ackNoESCAPE HATCH — leave unset in the normal flow. Binding a BRAND-NEW surface with no calibration content (no design_notes/voice_note/references/overrides) is REFUSED, because that is the fingerprint of a skipped kickoff interview. Only if the user was genuinely interviewed and chose to skip every optional dimension, set this to a one-line note affirming that (e.g. 'user interviewed 2026-07-04, declined all dimension calibration'). It is recorded on the binding so the deliberate skip is auditable. Never set it to work around asking the user.
Behavior5/5

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

The description extensively discloses behavioral details beyond annotations: it persists to a file (~/.raven/taste/<profile>.surfaces.json), performs upserts, carries forward omitted fields, refuses empty bindings, and generates consistency_warnings and build_hints. Even though annotations indicate destructiveHint=true, the description clarifies the mutation behavior (upsert) and safety mechanisms (carry-forward), aligning with and enriching the annotation signal.

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

Conciseness3/5

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

The description is long and packed with information, which is necessary given the tool's complexity (9 parameters, nested objects, multiple side effects). However, it lacks structural elements like bullet points or section breaks, making it dense. The first sentence effectively states the purpose, but subsequent details could be more concise. It earns a 3 for being appropriately detailed yet somewhat verbose.

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 no output schema, the description adequately covers the tool's behavior: it explains the binding process, failure conditions (empty calibration), carry-forward logic, consistency checks, and build hints. It also describes the relationship with audit_taste. While it could mention more about error cases or parameter validation, the description is largely complete for an agent to use the tool correctly.

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 schema already documents each parameter's meaning. The description adds value by explaining cross-parameter interactions, such as how references are consistency-checked against design_notes, how omitted parameters carry forward, and how the surface string is used for scope matching. This behavioral context enhances understanding beyond mere schema definitions.

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 description clearly states the tool's purpose: 'Persist a project's surface calibration for a taste profile — the answers from get_taste_interview.' It specifies the verb 'bind' and resource 'taste surface', distinguishing it from sibling tools like audit_taste (applies bindings) and get_taste_interview (produces interview data). The purpose is unambiguous and specific.

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?

The description provides clear usage context: run get_taste_interview first, ask the user, then bind answers. It includes constraints like refusing bindings with no calibration content and the uncalibrated_ack escape hatch for deliberate empty submissions. However, it does not explicitly compare with alternative tools like record_taste_decision, so some guidance on when to use this vs. others is implicit rather than explicit.

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

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/rhinocap/raven-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server