Skip to main content
Glama

Box the cards on a screenshot

suggest_regions

Boxes the cards on a screenshot in the brand kit (an upload or a recording frame) with a vision model, crops each and saves them on the asset. Captured pages already have their cards boxed from the page itself. 2 credits, nothing when it finds no card whose words read at 20 px in a promo.

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": {
      "brand_id": "<brand_id>",
      "asset_id": "<asset_id>"
    },
    "name": "suggest_regions"
  }
}

Input Schema

NameRequiredDescriptionDefault
modelNoA gateway vision model; the cheapest that passed the eval by default
namesNoCards to be sure of, by their heading
asset_idYesA screenshot in the brand kit (get_brand lists them): an upload or a recording frame
brand_idYesA brand kit from list_brands (id or name). Brings the colours, fonts, logo, website and default copy (headline, call to action, small print); use instead of brand.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare that this is a non-read-only, non-destructive, closed-world operation, and the description adds useful behavior beyond that: crops are saved onto the asset, a vision model is used, it costs 2 credits, and there is a no-charge no-card condition. It does not explain what happens to existing crops or what is returned, keeping it short of a 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?

Two sentences, front-loaded with the action, then the captured-page caveat and cost condition. The phrasing around 'words read at 20 px' is dense but purposeful and no sentence is wasted.

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?

For a write tool with annotations and no output schema, the description covers trigger conditions, mutation behavior, cost, and the no-op case. It leaves the resulting asset state and exact return behavior somewhat unspecified, but the essential invocation context is present.

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 all four parameters already documented in the schema, so the baseline is 3. The description mainly repeats that the asset is an upload or recording frame and does not add meaning for the model or names parameters.

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 ('Boxes the cards'), a specific resource ('screenshot in the brand kit'), and the mechanism (vision model, crops saved on the asset). It also distinguishes the captured-page case where cards are already boxed from the page itself, so an agent can tell what this tool is for.

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?

Explicitly excludes captured pages, which 'already have their cards boxed from the page itself,' and discloses the 2-credit cost plus the no-charge condition when no qualifying card is found. It does not name a sibling alternative for other image types, so it is clear but not fully exhaustive.

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