Skip to main content
Glama

Colour Memory

by io.github.DigbyO

Archive Report Brief

archive_report_brief
Read-only

One-call complete archive research package for a document, PDF, or editorial brief. Input: title, audience, themes, archives to draw from, things to avoid, number of colours. Output: ranked colour cards with full provenance, story order, source confidence flags, pull quote, CTA line, CSS tokens, image prompt for Midjourney/Flux/DALLE, editorial argument, weakest and strongest entries identified. Replaces chaining archive_search + get_colour_card + cliche_breaker + agent_brief separately. Two Claude calls total. This is the endpoint for building premium archive documents, PDFs, briefs, and editorial content. Use this first for any document workflow.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
avoidNoTopics to suppress e.g. ['arsenic wallpaper', 'Wedgwood blue']
titleNoDocument title e.g. 'The Colours of Georgian Power'
themesYesResearch themes e.g. ['racing silks', 'EIC trade', 'Keats']
archivesNoArchives to search e.g. ['RacingSilks', 'EIC', 'Keats', 'Dickens']
audienceNoTarget audience e.g. 'serious Georgian collector'
n_coloursNoNumber of colours to return (default 8, max 16)
period_endNoHard period gate: exclude entries dated after this year. Default 9999 (no upper bound).
period_startNoHard period gate: exclude entries dated before this year. Default 0 (no lower bound).
allow_partialNoIf false (default), returning fewer cards than requested sets ok=false with error_code INSUFFICIENT_PALETTE_RESULTS instead of a silent short 'success'. Set true to accept a short result.
output_formatNoReserved for future use -- currently accepted but has no effect on the response shape (the endpoint always returns the full report).
strict_sourcesNoOnly return entries with named primary sources (default true)
family_card_modeNoHow near-identical cultivars/records are presented. 'auto' (default): current behaviour, groups into family cards above the standard ΔE threshold. 'always': widens the clustering threshold so more near-duplicates group into family cards. 'conservative': suppresses family cards over max_family_card_share of the deck, instead promoting one hero cultivar per suppressed family with the rest folded into that card's also_supported_by list (never dissolved back into separate near-duplicate swatches).
confidence_thresholdNoMinimum confidence score (0.0-1.0) for an entry to be included. Default 0.5 filters out weakly-matched stubs.
max_family_card_shareNoConservative mode only: maximum fraction (0.0-1.0, default 0.5) of presented cards that may be family cards before excess families are suppressed to hero cards. Ignored in auto/always modes.
minimum_claim_strengthNoHard evidence-grade floor: A, B, C, D, or E. Never silently relaxed.
strict_semantic_colourNoDefault false. When true, excludes entries whose quoted colour language contradicts their stored hex (e.g. a record naming 'Prussian blue' whose hex is actually a pale cream) rather than presenting them as normal evidence. Never alters hex values, only excludes flagged ones.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, and the description adds meaningful behavioral context beyond that: 'Two Claude calls total' (resource usage), hard period gates, strict evidence floors ('Never silently relaxed'), and error handling for insufficient results (INSUFFICIENT_PALETTE_RESULTS). It contradicts nothing in the annotations.

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?

The description is a single dense paragraph that front-loads the core value proposition. It is fairly long, but each sentence adds necessary context (output list, usage priority, alternatives). The output list may duplicate what the output schema already conveys, slightly bloating the text, but it remains well-structured.

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?

Given the tool's complexity (16 parameters, output schema, minimal annotations), the description provides a complete high-level orientation: purpose, expected outputs, usage guidance, and alternatives. Detailed parameter behavior is left to the exhaustive schema, so there are no critical gaps for an agent to select and call the tool effectively.

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 detailed per-parameter descriptions. The tool description only paraphrases a subset of parameters (title, audience, themes, archives, avoid, n_colours) without adding new semantics or format details beyond what the schema already provides, so the baseline 3 is appropriate.

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 opens with a specific, action-oriented claim: 'One-call complete archive research package for a document, PDF, or editorial brief.' It clearly differentiates from siblings by explicitly stating it replaces chaining archive_search + get_colour_card + cliche_breaker + agent_brief, making the tool's unique value unmistakable.

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?

It gives explicit when-to-use instruction: 'Use this first for any document workflow.' It also names the alternatives it replaces, providing clear guidance on when this tool should be selected over the pointed-to sibling tools.

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

All Colour Memory toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.8/5.0
Disambiguation2/5

With 88 tools, there is substantial overlap: colour_passport vs colour_dna vs colour_metrics vs colour_cultural_risk are explicit components of the same object; palette_concept vs palette_strict vs palette_generate vs palette_heritage overlap heavily; and four image extraction tools exist (extract_image_colours, image_palette, palette_extact, ingest_image). Although descriptions are detailed and tool_guide exists, an agent will frequently struggle to select the correct tool unambiguously.

Naming Consistency5/5

Nearly all tools follow a consistent snake_case noun_verb or domain-prefixed pattern (colour_*, palette_*, brand_*, archive_*, project_*, accessibility_*). The naming is uniform and predictable, with no mixing of styles or verb conventions across the set.

Tool Count1/5

88 tools is an extreme count for an MCP server. Even honoring the broad domain, the rubric places 50+ at the extreme end, and the high overlap between compound and individual tools suggests many could be consolidated or exposed as sub-resources rather than top-level tools.

Completeness5/5

The tool surface covers the full colour lifecycle: lookup, analysis, palettes, brand systems, accessibility, image extraction, interior design, archival research, reports, PDF generation, and project management. Workflows have clear entry points and few dead ends, and the presence of compound tools further closes integration gaps.

Resources