Skip to main content
Glama

Generate Colour Direction for Another AI

agent_brief
Read-only

Generate a complete colour direction package for another AI agent or image generation model. Fetches a historically grounded archive palette from the concept, then produces: an agent brief (colour direction in prose), colour tokens with hex values and roles, a model-specific image generation prompt, a negative prompt, and lighting notes. Supports midjourney, flux, dalle, stable_diffusion. Example: task='luxury hotel bedroom', concept='Ottoman winter luxury', model='midjourney'. Use this to make Colour Memory the colour layer for other AI systems. Archive-grounded retrieval is evidence-filtered: entries with claim_role='reject' (no primary source and no period connection), stub entries, blank-source entries, and entries below minimum_claim_strength are never selected. If fewer than palette_size colours pass these filters, the call returns an honest incomplete result (ok:false, error_code:INSUFFICIENT_EVIDENCE_ELIGIBLE_PALETTE) rather than padding the palette with rejected or weak evidence. Negative constraints (from 'avoid' or negation phrases in concept like 'must never', 'without', 'not') are also applied to retrieval, not just flagged afterward -- a brief that says a wedding must never feel funereal will not surface mourning-themed colours in the first place. locked_palette calls skip evidence filtering entirely since the caller is supplying colours directly, not requesting archive evidence.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "task": "<task>",
      "concept": "<concept>"
    },
    "name": "agent_brief"
  }
}

Input Schema

NameRequiredDescriptionDefault
taskYesWhat the other AI needs to generate e.g. 'luxury hotel bedroom image'
avoidNoOptional: terms/associations to keep out of retrieval e.g. ['mourning', 'funeral black']. Affects retrieval directly, not just post-hoc flagging.
modelNoTarget model: midjourney, flux, dalle, stable_diffusionmidjourney
archiveNoOptional: restrict palette query to this archive e.g. georgianpleasures, japan, china
conceptYesColour concept to draw from e.g. 'Ottoman winter luxury', 'Victorian mourning'. Negation phrases ('must never', 'without', 'not X') are extracted and kept out of retrieval.
style_notesNoOptional: additional style direction e.g. 'matte surfaces only', 'no gold'
palette_sizeNoNumber of archive colours to include (default 5, max 8)
locked_paletteNoOptional: list of hex values to use exclusively. When provided, no archive query is run and no evidence filtering applies; these exact colours are used as-is. Prevents palette drift.
allowed_archivesNoOptional: list of allowed archive names. Query restricted to these archives only.
minimum_claim_strengthNoEvidence-grade floor for archive-grounded retrieval (default 'C'). Grade controls documentary strength; claim_role='reject' entries are excluded regardless of how low this is set. Not applied to locked_palette calls.C

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / locked_palette / description
      Previous value: -"Optional: list of hex values to use exclusively. When provided, no archive query is run and no evidence filtering applies — these exact colours are used as-is. Prevents palette drift."New value: +"Optional: list of hex values to use exclusively. When provided, no archive query is run and no evidence filtering applies; these exact colours are used as-is. Prevents palette drift."
  2. Changed1 schema field changed
    • addedInput schema / properties / minimum_claim_strength / default
      Added value: +"C"
  3. Changed4 schema fields changed
    • addedInput schema / properties / avoid
      Added value: +{
      +  "default": [],
      +  "description": "Optional: terms/associations to keep out of retrieval e.g. ['mourning', 'funeral black']. Affects retrieval directly, not just post-hoc flagging.",
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
    • changedInput schema / properties / concept / description
      Previous value: -"Colour concept to draw from e.g. 'Ottoman winter luxury', 'Victorian mourning'"New value: +"Colour concept to draw from e.g. 'Ottoman winter luxury', 'Victorian mourning'. Negation phrases ('must never', 'without', 'not X') are extracted and kept out of retrieval."
    • changedInput schema / properties / locked_palette / description
      Previous value: -"Optional: list of hex values to use exclusively. When provided, no archive query is run — these exact colours are used. Prevents palette drift."New value: +"Optional: list of hex values to use exclusively. When provided, no archive query is run and no evidence filtering applies — these exact colours are used as-is. Prevents palette drift."
    • addedInput schema / properties / minimum_claim_strength
      Added value: +{
      +  "description": "Evidence-grade floor for archive-grounded retrieval (default 'C'). Grade controls documentary strength; claim_role='reject' entries are excluded regardless of how low this is set. Not applied to locked_palette calls.",
      +  "enum": [
      +    "A",
      +    "B",
      +    "C",
      +    "D",
      +    "E"
      +  ],
      +  "type": "string"
      +}
  4. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "additionalProperties": true,
      +  "description": "Structured JSON response. Shape varies by tool; most return an 'ok' boolean plus a 'result' or 'results' field with the tool's data payload.",
      +  "type": "object"
      +}
  5. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -{
      -  "properties": {
      -    "error": {
      -      "type": "string"
      -    },
      -    "ok": {
      -      "type": "boolean"
      -    },
      -    "result": {
      -      "type": [
      -        "object",
      -        "array",
      -        "string",
      -        "null"
      -      ]
      -    }
      -  },
      -  "type": "object"
      -}New value: +null
  6. First observed

TDQS

A4.4/5.0
Behavior5/5

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

Annotations declare only readOnlyHint=true, and the description goes far beyond that: it discloses evidence filtering rules (claim_role='reject', stubs, blank sources, minimum_claim_strength floor), the honest-failure contract (ok:false with error_code INSUFFICIENT_EVIDENCE_ELIGIBLE_PALETTE instead of padding), that negative constraints feed retrieval rather than post-hoc flagging, and that locked_palette bypasses filtering entirely. These are exactly the behavioral traits that change how an agent plans and interprets a call.

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 front-loaded with purpose and a bulleted artifact list, then moves into filtering and failure behavior in a logical order. It is somewhat long and repeats the 'negation affects retrieval, not just flagging' point in both the body and the avoid parameter, which is mild redundancy rather than waste.

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 10-parameter tool with an output schema and minimal annotations, this description covers what it produces, how retrieval is gated, what happens on insufficient evidence, and how the locked path differs — leaving nothing an agent needs before calling. Return-value formatting is correctly left to the output schema.

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 coverage is 100% and the parameter descriptions already cover defaults, enums, and the retrieval semantics of avoid, minimum_claim_strength, and locked_palette. The body text adds an illustrative task/concept/model combination and reinforces that negation in 'concept' is extracted, but it largely restates what the schema documents rather than adding new per-parameter meaning, 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?

The description opens with a specific verb+resource ('Generate a complete colour direction package') and then enumerates the exact artifacts produced: agent brief prose, colour tokens with hex values and roles, model-specific image prompt, negative prompt, and lighting notes. The example call and the 'make Colour Memory the colour layer for other AI systems' framing let an agent distinguish this bundle-producing tool from single-purpose siblings like palette_generate or colour_card 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 Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives a clear usage context ('Use this to make Colour Memory the colour layer for other AI systems'), a concrete example invocation with task/concept/model, and explicitly states the locked_palette path skips evidence filtering. What it lacks is a named alternative or an explicit 'when not to use this — use X instead' exclusion, so routing against the many sibling brief tools is still left partly to inference.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources