Skip to main content
Glama

Create a photo filter

create_filter

Create a new photo filter on this operator's account from a description of the look they want — 'warm and slightly faded', 'high contrast black and white'. Translate the description into the adjustment numbers yourself; the ranges are in the schema. Call this only when the operator asks for a filter to be CREATED. It does not change an existing filter, and there is no tool that does — to edit or delete one, send them to the dashboard. Creating the same filter twice makes two filters, so do not retry a call that may have gone through.

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

Input Schema

NameRequiredDescriptionDefault
nameYesWhat the operator will see in their filter list. Use their words if they named it; otherwise a short descriptive name, not 'Untitled'.
isPublicNoLeave unset unless the operator explicitly asks for the filter to be shared. Default is private to their account.
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
idNo
kindYes
nameNo
isPublicNo
previewUrlNo
adjustmentsNo
dashboardUrlNo

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

A4.7/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false, idempotentHint=false and destructiveHint=false, so the safety profile is covered. The description adds real consequence beyond that: a repeated call produces two distinct filters and a possibly-completed call should not be retried — actionable operational detail the hints alone do not convey. It does not add anything about auth/permissions or how the created filter is returned, so it stops short of 5.

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?

It is five tight sentences, front-loaded with purpose, then the translation instruction, then when-to-use, then the no-edit fallback and the duplicate-call warning. No sentence repeats the schema or the annotations, and the most consequential warning (do not retry) lands last where it is salient.

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 presence means return values need not be explained, and annotations cover the safety profile. What remains for a creation tool — the trigger condition, the absence of any edit/delete path, and the non-idempotency hazard — is all stated, and the nested adjustments object is fully documented in-schema.

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%, so the per-slider ranges and neutral values are already fully documented, and a baseline of 3 would be defensible. The description nevertheless adds meaning the schema does not: the core interpretive task is to translate a qualitative phrase like "warm and slightly faded" into numbers yourself, with "the ranges are in the schema" pointing the agent at the right reference. That framing of how to derive the parameters is genuine added value.

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 opening sentence names a specific verb and resource ("Create a new photo filter on this operator's account") and immediately scopes the input as a natural-language description of the look. It is distinguishable from siblings such as preview_filter or refine_frame because it says the artifact is a new saved filter, not a preview or a booth/frame change.

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 an explicit trigger ("Call this only when the operator asks for a filter to be CREATED") and explicit exclusions ("It does not change an existing filter, and there is no tool that does"), plus a fallback route ("send them to the dashboard"). The only omitted routing is to the sibling preview_filter for trying a look before saving, which is a minor gap rather than an ambiguity.

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.