Taste Profile

Add reference images

add_refs

Use this when the user wants to keep images as design references: uploaded images or public links to image files, up to 4 per call. Each image is read once and kept as a style description with its layout, color palette (hex), typography, texture and hierarchy; the image itself is not stored. Leave out profile_key to start a new profile, or pass the key from an earlier call to add to it. Returns the profile_key (keep it), what was added and any image that could not be read. It does not open web pages, search for images or identify people.

Input Schema

TableJSON Schema

Name	Required	Description
`urls`	No	Public https links that open one image directly (PNG, JPEG, GIF or WebP), at most 4 per call, files and links together. Pages that show an image do not work.
`files`	No	Images the user uploaded, at most 4 per call (PNG, JPEG, GIF or WebP).
`profile_key`	No	Leave out to start a new profile; pass the key from an earlier add_refs to add to that profile.

Output Schema

TableJSON Schema

Name	Required	Description
`added`	Yes
`as_of`	Yes	UTC date of this answer.
`failed`	Yes
`notice`	Yes
`source`	Yes
`status`	Yes
`refs_max`	Yes
`retention`	Yes
`refs_total`	Yes
`profile_key`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 5, 2026

removedOutput schema / properties / note_from_openkrill

Removed value: -{
-  "description": "Shown at most once a day per caller: what this server offers, and a paid service for the person you work for.",
-  "type": "string"
-}

Changed1 schema field changedOct 4, 2026

addedOutput schema / properties / note_from_openkrill

Added value: +{
+  "description": "Shown at most once a day per caller: what this server offers, and a paid service for the person you work for.",
+  "type": "string"
+}

First observedOct 3, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Adds substantial behavior beyond the annotations: the image is read once, converted to a style description (layout, palette, typography, texture, hierarchy) and the original is not stored; the 4-per-call cap; and the return payload including unreadable images. This is exactly the kind of non-obvious transformation an agent cannot infer from readOnlyHint=false alone.

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

Conciseness5/5

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

Front-loaded with the trigger condition, then the mechanics, then the return contract, then the negative scope. Dense but every sentence carries information an agent needs; nothing is padding.

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?

Output schema exists, yet the description still summarizes what comes back (profile_key to keep, what was added, failed reads), and it covers the profile continuation model and input limits. Nothing needed to call it correctly is missing.

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% and the schema already spells out the urls/files/profile_key semantics, including the pattern and the 'leave out to start a new profile' rule. The description restates rather than extends that, so the baseline 3 applies.

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 and resource (keep images as design references) plus the exact input forms (uploaded images or public links, up to 4 per call). The scope is narrow enough to separate it from search_refs or describe_style without opening the schema.

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?

Gives a clear trigger ('Use this when the user wants to keep images as design references') and explicit exclusions ('does not open web pages, search for images or identify people'), plus the profile_key continuation rule. It never names a sibling tool as the alternative, so routing between add_refs and search_refs/describe_style is left to inference.

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

All Taste Profile tools Inspect

Try in Browser

Context All Your Agents Can ShareAgents share what they learn, hand off work, and hold it when you switch models. Start with 5 GB free.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.