Skip to main content
Glama

Check a deal

check_deal

Deal Desk profit check for one card the user may buy: the estimated max buy price, a suggested opening offer and, with an asking price, BUY / NEGOTIATE / PASS / NOT_ENOUGH_DATA with the estimated profit. Identify the card with search_cards before checking (use its cardId); for a slab, read the grading company and grade off the slab label in the photo. Slabs are priced from the 3 most recent sales (data color GREEN / YELLOW / RED by how recent); raw cards from the market price (GREY) and a grade-then-sell path. For a raw card, pass estimateId of the user's finished pre-grade to use its grade range. Every number is an estimate, never a guarantee; read the summary to the user. Each check is saved to the session (pass_deal marks one passed). If the result has alerts, show them to the user before anything else.

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": {
      "grader": "<grader>"
    },
    "name": "check_deal"
  }
}

Input Schema

NameRequiredDescriptionDefault
gameNoDefault pokemon.
gradeNoThe grade on the slab label, e.g. "10" or "9.5". Not needed for RAW.
cardIdNoSlabLineage card id from search_cards (any row of the card). Give cardId or the catalog id; one of them is required.
graderYesThe slab's grading company read off the label: PSA, TAG, CGC, BGS (Beckett), SGC, ACE or another; RAW for an ungraded card.
estimateIdNoRaw cards: the user's pre-grade id (from my_pregrades).
askingPriceNoThe seller's asking price in USD.
scrydexCardIdNoOr the card's catalog id, e.g. "sv3pt5-199" (when you have it instead of cardId).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Beyond the annotations (readOnlyHint=false, openWorldHint=true, idempotentHint=false), the description discloses the side effect that each check is persisted to the session and that pass_deal marks one passed, plus that alerts must be surfaced first. It also deflates expectations ('Every number is an estimate, never a guarantee; read the summary to the user') and explains the GREEN/YELLOW/RED and GREY data-quality coding, which the 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?

The most decision-relevant content (what it returns, identify-first) is front-loaded, and every sentence carries information: verdict semantics, slab-vs-raw pricing, session persistence, caveats, alert ordering. It is dense rather than bloated, though the parenthetical asides make single sentences carry two ideas.

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 7-parameter tool with no output schema, the description covers the return shape (verdict, profit, max buy, opening offer), the state change (session save), and how to present results to the user. Minor gaps remain, such as whether repeated checks differ from the first (non-idempotent) or any cost/latency of the open-world pricing lookup.

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; the description earns above that by explaining the cardId/search_cards link and the conditional rule that estimateId comes from a finished pre-grade and feeds the grade range for raw cards. It still leaves the interaction of game and scrydexCardId versus cardId (which the schema calls mutually exclusive) to the schema text.

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 clause names a specific verb and resource ('Deal Desk profit check for one card') and enumerates the concrete outputs: estimated max buy price, suggested opening offer, and a BUY/NEGOTIATE/PASS/NOT_ENOUGH_DATA verdict with estimated profit. That is distinguishable at a glance from siblings like search_cards (identification) or get_card_price (market price lookup).

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?

It gives a clear prerequisite workflow ('Identify the card with search_cards before checking (use its cardId)') and conditional branches (slab vs raw, raw + finished pre-grade -> pass estimateId). What it doesn't state is when NOT to use it, e.g. how it differs from find_deals or listing_checkup for the same decision, so there is a small inference gap.

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