Skip to main content
Glama

PokeInvest Pokemon card prices

identify_card_photo

Read-onlyIdempotent

Identify a Pokemon card from a photo URL (raw card or slab, any angle): the top candidates with PokeInvest IDs, prices and population. Right card on 95.6% of 1,000 real eBay photos, 96.5% in the top 3. Same-art printings (1st Edition, reverse holo) are the usual miss, 87% exact; show the top 3.

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": {
      "image_url": "<image_url>"
    },
    "name": "identify_card_photo"
  }
}

Input Schema

NameRequiredDescriptionDefault
image_urlYespublic https URL of the photo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior5/5

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

Annotations already declare this a safe, idempotent, closed-world read, and the description adds substantial context beyond them: what is returned (candidates with PokeInvest IDs, prices, population), measured accuracy (95.6% top-1 on 1,000 real eBay photos, 96.5% top-3), and the known failure mode (same-art printings like 1st Edition and reverse holo, 87% exact). That failure-mode disclosure is exactly the kind of thing annotations cannot convey.

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 purpose, then return contents, then accuracy and the actionable 'show the top 3' instruction — no filler sentences. It is somewhat number-dense (three separate percentage figures), but each stat supports a decision about whether to trust or re-rank the results.

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?

There is no output schema, so the description must describe the return value, and it does (candidates with PokeInvest IDs, prices, population, ranked with a top-3 recommendation). For a one-parameter identification tool this is nearly complete; only the no-match/error behavior is left unspecified.

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?

With a single parameter at 100% schema coverage, the baseline is 3; the description earns an extra point by constraining what the URL may contain ('raw card or slab, any angle'), which the schema's 'public https URL of the photo' does not say. It still doesn't mention image format, resolution, or size limits.

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 ('Identify a Pokemon card from a photo URL') and immediately scopes the accepted input modality ('raw card or slab, any angle'), which is what distinguishes it from the text-based siblings like search_cards and get_card_prices. An agent knows exactly what this tool is for without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives input-side guidance (photo can be a raw card or slab, any angle) and output-side guidance ('show the top 3'), which is genuinely actionable. However, it never says when to prefer this over search_cards or get_card_prices, nor what to do when no candidate is returned, so routing must be inferred from the name.

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