Skip to main content
Glama

identify_card

Use this for any question that starts with photos and asks what the trading card is. Send a front JPEG, PNG, or WebP data URL (min 250px, keep under ~350KB); a back photo is optional and is not used, and the call typically takes 15-20 seconds. It returns a catalog match for Pokémon (English and Japanese), Magic: The Gathering, Yu-Gi-Oh!, One Piece, and Riftbound, including set_id, game_id, and release_date when known, not a grade or a use of the in-app scan allowance. Free, limited to 10 per minute and 20 per key per UTC day, on a cap separate from catalog search.

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": {
      "front": "<front>"
    },
    "name": "identify_card"
  }
}

Input Schema

NameRequiredDescriptionDefault
backNoOptional. JPEG, PNG, or WebP data URL (data:image/jpeg;base64,...). Each side at least 250px, at most 4000px; keep each photo under 342KB (hard cap 684KB). Accepted but not used; identification uses the front image only.
frontYesRequired. JPEG, PNG, or WebP data URL (data:image/jpeg;base64,...). Each side at least 250px, at most 4000px; keep each photo under 342KB (hard cap 684KB). identify_card typically takes 15–20 seconds.
idempotency_keyNoUnique retry key

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • changedInput schema / properties / back / description
      Previous value: -"Optional back photo. Accepted but not used; identification uses the front image only."New value: +"Optional. JPEG, PNG, or WebP data URL (data:image/jpeg;base64,...). Each side at least 250px, at most 4000px; keep each photo under 342KB (hard cap 684KB). Accepted but not used; identification uses the front image only."
    • changedInput schema / properties / front / description
      Previous value: -"Front photo as a data:image/jpeg;base64,... URL. Required."New value: +"Required. JPEG, PNG, or WebP data URL (data:image/jpeg;base64,...). Each side at least 250px, at most 4000px; keep each photo under 342KB (hard cap 684KB). identify_card typically takes 15–20 seconds."
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "additionalProperties": true,
      +  "type": "object"
      +}
  2. Changed3 schema fields changed
    • changedInput schema / properties / back / description
      Previous value: -"Back photo data URL"New value: +"Optional back photo. Accepted but not used; identification uses the front image only."
    • changedInput schema / properties / front / description
      Previous value: -"Front photo data URL"New value: +"Front photo as a data:image/jpeg;base64,... URL. Required."
    • changedInput schema / required
      Previous value: -[
      -  "front",
      -  "back"
      -]New value: +[
      +  "front"
      +]
  3. First observed

TDQS

A4.2/5.0
Behavior3/5

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

No annotations are provided, so the description carries the full burden, and it does well here: latency (15-20s), cost (free), rate limits (10/min, 20/day per key), and a distinct quota pool are all disclosed, plus the notable behavior that the back image is accepted but ignored. A 3 rather than higher because failure modes (no match found, low-confidence results, oversized image rejection) and what a non-match response looks like are not described.

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?

Front-loaded with the triggering condition, then inputs, then returns, then limits – a sensible order with no filler sentences. It is dense, though: the parenthetical catalog list and the quota sentence pack a lot into a single paragraph and could be trimmed slightly.

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?

Given an output schema exists, the description needn't enumerate return fields, yet it still names set_id, game_id, and release_date to set expectations. Image constraints, latency, supported games, exclusions, and quotas are all covered, leaving nothing an agent needs in order to call it correctly.

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 baseline is 3, and the description adds a little: the front is the only image used, minimum 250px, keep under ~350KB. Those size hints duplicate the schema's own descriptions, and the idempotency_key is never mentioned in the description, so the added value is modest.

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+resource ('identify_card' implied by 'Send a front JPEG... returns a catalog match') and scopes it precisely: it answers 'what the trading card is' from a photo. Explicitly excludes grading and in-app scan allowance, which separates it from grade_card and the scanning flow, so an agent can discriminate it from siblings 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?

Gives a clear triggering condition ('any question that starts with photos and asks what the trading card is') and two clear exclusions ('not a grade', 'not a use of the in-app scan allowance', 'cap separate from catalog search'). It does not name a specific sibling to use instead for those excluded cases, which keeps it 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.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources