Skip to main content
Glama

Check a trade

check_trade

Deal Desk pre-trade check: the cards the user gives (outgoing) and gets (incoming), plus cash either way, valued after selling costs → TRADE / COUNTER (with the cash to ask for) / PASS, or NOT_ENOUGH_DATA naming the card without a value (ask the user for its value and pass it as value). Identify each card with search_cards before checking. It is a check: nothing is recorded to the collection. 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": {
      "incoming": "<incoming>"
    },
    "name": "check_trade"
  }
}

Input Schema

NameRequiredDescriptionDefault
cashInNoCash the user receives in USD.
cashOutNoCash the user pays in USD.
incomingYes
outgoingNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Adds substantial context beyond the sparse annotations: valuation is done after selling costs, the four possible verdicts are spelled out, no writes occur, and alerts must be surfaced first. The only wobble is that annotations declare readOnlyHint=false while the description insists nothing is recorded — not a contradiction of destructiveHint=false, and plausibly due to live pricing lookups, but it is left unexplained.

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-loads the purpose, then the data shape, then the outcome set, then the workflow rules — a sensible order with no filler. The first sentence is long and arrow-packed, but every clause (after-selling-costs valuation, the three verdicts) carries information an agent needs.

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?

With no output schema, the description takes on the burden of describing return values and does so fully, including the ambiguous NOT_ENOUGH_DATA case. Minor omissions remain for a fairly complex tool: the 1–10 card limit per side and what happens on an unresolvable cardId are only in the schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema's top-level arrays carry no direction semantics, and the description supplies them precisely: 'outgoing' is what the user gives, 'incoming' is what the user gets, plus 'cash either way' covering cashIn/cashOut. It also ties the NOT_ENOUGH_DATA recovery to the schema's 'value' field, which is meaning the schema alone does not convey.

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 ('Deal Desk pre-trade check') and enumerates the exact outcome space: TRADE / COUNTER / PASS / NOT_ENOUGH_DATA. It also explicitly separates itself from the recording sibling by stating 'It is a check: nothing is recorded to the collection', so an agent can tell it apart from record_trade without opening either 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 concrete prerequisite workflow ('Identify each card with search_cards before checking') and a recovery path for NOT_ENOUGH_DATA ('ask the user for its value and pass it as value'), plus an ordering rule for alerts. It stops short of naming the alternative tool (record_trade) that should be used when the user actually wants the trade persisted, leaving that inference to the phrase 'nothing is recorded'.

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