Skip to main content
Glama
agenthouse-org

dealdesk-mcp

dealdesk.create_quote

Create a classic draft quote with optional lineItems, options, and groups. Prefer companyId/contactId (Customer Directory) so snapshots are resolved server-side.

Instructions

Create a classic draft quote with optional lineItems, options, and groups. Prefer companyId/contactId (Customer Directory) so snapshots are resolved server-side. Use this path for free-form / open positions; use create_quote_from_configuration for CPQ.

Input Schema

NameRequiredDescriptionDefault
titleYes
groupsNoSelection groups (selectionType single|multi, lineItems[], …)
optionsNoOptional positions (defaultSelected, quantityEditable, …)
currencyNo
languageNo
companyIdNoCustomer Directory company id
contactIdNoCustomer Directory contact id
lineItemsNoIncluded base positions (label, quantity, unitPrice, …)
projectIdNoDealDesk project id. Omit when the OAuth token or API key authorizes exactly one project. Required when Connect authorized several projects.
opportunityIdNo
servicePeriodNoFirst-class commercial period on quotes and orders. start/end accept ISO dates or YYYY-MM (month expands to first/last day). single is derived and read-only.
customerReferenceNoOptional explicit directory refs (companyId/contactId/relationshipId)

Output Schema

NameRequiredDescriptionDefault
quoteYesQuote status, totals, and optional analytics/shares. Extra fields live on this object, not beside it.
idempotentReplayNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.1.2
    • addedInput schema / properties / servicePeriod
      Added value: +{
      +  "additionalProperties": false,
      +  "description": "First-class commercial period on quotes and orders. start/end accept ISO dates or YYYY-MM (month expands to first/last day). single is derived and read-only.",
      +  "nullable": true,
      +  "properties": {
      +    "end": {
      +      "nullable": true,
      +      "type": "string"
      +    },
      +    "start": {
      +      "nullable": true,
      +      "type": "string"
      +    }
      +  },
      +  "type": "object"
      +}
  2. Changed4 schema fields changedv0.1.1
    • changedInput schema / properties / projectId / description
      Previous value: -"DealDesk project id (must match API key / OAuth project)"New value: +"DealDesk project id. Omit when the OAuth token or API key authorizes exactly one project. Required when Connect authorized several projects."
    • changedInput schema / required
      Previous value: -[
      -  "projectId",
      -  "title"
      -]New value: +[
      +  "title"
      +]
    • changedOutput schema / additionalProperties
      Previous value: -falseNew value: +true
    • changedOutput schema / properties / quote / description
      Previous value: -"Quote summary shown in the quote-totals widget"New value: +"Quote status, totals, and optional analytics/shares. Extra fields live on this object, not beside it."
  3. First observedv0.1.0

TDQS

A4.4/5.0
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. It reveals that the result is a draft and that snapshot resolution happens server-side when directory IDs are supplied, which is useful non-obvious behavior. However, it says nothing about permission requirements, what happens to unresolved snapshot data, or the mutation's reversibility.

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?

Three sentences, front-loaded with the core action, then the preferred calling pattern, then the alternative-tool routing. No filler and nothing repeated from the schema.

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 12-parameter mutation with nested objects and an output schema (so return values needn't be explained), the description covers the structural choice and the key ID preference. Minor gaps remain on how groups/options interact and on projectId authorization behavior, though the schema already documents the latter.

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 67%, and the description adds genuine meaning beyond it: it explains the payoff of companyId/contactId (server-side snapshot resolution) and frames lineItems vs options vs groups as included base positions vs optional positions vs selection groups. It does not clarify currency/language defaults or the customerReference vs top-level ID relationship.

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 ('Create a classic draft quote') plus the optional constructs it accepts (lineItems, options, groups), and explicitly names the sibling create_quote_from_configuration as the CPQ counterpart. An agent can distinguish it from the many other quote tools 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 Guidelines5/5

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

Gives explicit routing: 'Use this path for free-form / open positions; use create_quote_from_configuration for CPQ.' It also advises preferring companyId/contactId (Customer Directory) so snapshots resolve server-side, which is actionable guidance on how to call it, not just when.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools