Skip to main content
Glama

Preview a photo filter

preview_filter
Read-onlyIdempotent

Show what a filter would look like BEFORE creating it: the Studio renders its sample photo (or the operator's own preview photo, if they set one in the dashboard) through the exact pipeline the booth uses, and returns an image URL. Free and read-only — call it whenever the operator is designing a filter, adjust the numbers from their reaction ('warmer', 'less contrast'), preview again, and call create_filter with the same adjustments only once they are happy. Some adjustments (shadows, highlights, whites, blacks, clarity, dehaze, vibrance, texture) are applied by the booth but cannot be shown here; the result lists them as notPreviewed so you can say so. Nothing is created by this tool.

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": {
      "adjustments": "<adjustments>"
    },
    "name": "preview_filter"
  }
}

Input Schema

NameRequiredDescriptionDefault
adjustmentsYesOnly include what the operator asked to change. An omitted adjustment keeps its neutral value; sending every field at its neutral value creates a filter that does nothing. A look is a few small moves, not every slider: most need 2-5 adjustments, each within about 25 of neutral (75-125 on the 0-200 scales) unless the operator asks for something strong ('high contrast', 'black and white'). Booth photos are faces under venue light, so keep skin believable: leave hueRotate at 0 unless they ask for a surreal colour shift (it turns skin green or blue), and keep tint within 15 of 0. Do not stack vignette, grain, clarity and dehaze to make it 'cinematic'; one of them, lightly, is usually the whole effect.

Output Schema

NameRequiredDescriptionDefault
kindYes
noteYes
sampleYes
previewedYes
previewUrlYes
adjustmentsYes
notPreviewedYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / adjustments / description
      Previous value: -"Only include what the operator asked to change. An omitted adjustment keeps its neutral value; sending every field at its neutral value creates a filter that does nothing."New value: +"Only include what the operator asked to change. An omitted adjustment keeps its neutral value; sending every field at its neutral value creates a filter that does nothing. A look is a few small moves, not every slider: most need 2-5 adjustments, each within about 25 of neutral (75-125 on the 0-200 scales) unless the operator asks for something strong ('high contrast', 'black and white'). Booth photos are faces under venue light, so keep skin believable: leave hueRotate at 0 unless they ask for a surreal colour shift (it turns skin green or blue), and keep tint within 15 of 0. Do not stack vignette, grain, clarity and dehaze to make it 'cinematic'; one of them, lightly, is usually the whole effect."
  2. Added

TDQS

A4.9/5.0
Behavior5/5

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

Annotations already cover read-only, idempotent and non-destructive, and the description adds real context beyond them: the call is free (no credits), it renders through the exact production pipeline, and 'Nothing is created by this tool.' It also discloses a genuine limitation — certain adjustments are applied by the booth but cannot be previewed and come back flagged in notPreviewed — which is exactly the kind of caveat an agent could not get from structured fields.

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?

The core purpose and the read-only/free guarantee are front-loaded, then the workflow, then the limitation. Every clause carries information an agent needs — there is no restatement of the name or title.

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 preview tool with a rich nested schema and an output schema already present, the description supplies exactly the missing pieces: the preview image source (Studio sample photo or the operator's own dashboard photo), the returned image URL, the notPreviewed field, and the handoff to create_filter. An agent could call it correctly without further information.

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 coverage is 100% and the nested adjustments object is heavily documented, so the baseline is 3; the description lifts it by naming which adjustments (shadows, highlights, whites, blacks, clarity, dehaze, vibrance) are not previewable, a distinction absent from the schema. It stops short of per-parameter guidance, and 'texture' is listed among non-previewable fields but does not exist in the schema, a minor drift.

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 ('Show what a filter would look like') and pins the scope precisely: a preview rendered through the exact booth pipeline, returning an image URL. It is immediately distinguishable from the sibling create_filter, which it explicitly defers to.

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?

Gives explicit when-to-use ('whenever the operator is designing a filter'), an iteration loop with the operator's reaction as feedback, and the when-not/alternative ('call create_filter with the same adjustments only once they are happy'). Nothing 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.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.