Skip to main content
Glama

Theme From Image

theme_from_image
Destructive

Generate up to three report themes from a local image, or apply a chosen theme as a custom report theme with a restorable, journalled write.

Instructions

Theme > Extract theme from image. Without choice: sends the local image to Datastudio's theme generator and returns up to 3 generated themes (colors, series, palette) plus report_fingerprint; nothing changes. With choice (0-based) and that fingerprint: stores the chosen theme as the report's custom theme and activates it, exactly as the dialog's Apply (fonts and other slots reset to the editor defaults, as in the UI). One journalled report write, restorable.

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": {
      "path": "<path>"
    },
    "name": "theme_from_image"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathYes
choiceNo
dry_runNo
report_idNo
expected_report_fingerprintNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.6.5

TDQS

A4/5.0
Behavior4/5

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

Goes well beyond the annotations by disclosing that the no-choice path changes nothing, that the commit path resets fonts and other slots to editor defaults (as in the UI), that it is a single journalled report write, and that it is restorable. The notable omission is dry_run, which defaults to true and therefore gates the write — the description describes the commit as unconditional, leaving the agent to discover the safety switch in the schema.

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?

Dense but front-loaded: the tool name prefix, the resource, and the two modes come before the edge cases, and every clause carries real information. The mid-sentence line break and stacked parentheticals make it slightly harder to scan than it needs to be.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Return shape is partly described and an output schema exists, and the write semantics are unusually well covered for a mutation tool. However, for a destructive, fingerprint-guarded, dry-run-defaulting tool, silently omitting dry_run and report_id leaves a real gap an agent must resolve from the raw 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?

With 0% schema description coverage the description must carry all five parameters, and it only explains path (local image), choice (0-based index), and expected_report_fingerprint (fingerprint from the prior call). dry_run — the most consequential parameter given a destructive default — and report_id are never mentioned, so coverage is roughly half.

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 ('Extract theme from image') and then splits the behavior into two precisely named modes: a generation-only mode and a commit mode. An agent can tell exactly what the tool produces in each case (up to 3 themes plus report_fingerprint, or a stored and activated custom theme).

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 clear when-to-use guidance for both branches: omit choice to generate candidates, supply choice plus the matching fingerprint to commit. It implies the two-call workflow without naming a distinct alternative tool or stating explicit exclusions, so it falls just short of a 5.

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

Deploy Server

Other Tools