Skip to main content
Glama
agenthouse-org

dealdesk-mcp

dealdesk.create_company

Creates a company record in the DealDesk customer directory. Provide projectId and legalName or name; externalId is optional and auto-generated when omitted.

Instructions

Create a company in the customer directory. Send legalName or name at the top level (name maps to legalName). externalId is optional and auto-generated as local-company- when omitted — do not require fields.externalId.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameNoAlias for legalName when legalName is omitted (mapped server-side)
taxIdNo
fieldsNoOptional extras (customFields, addresses, …). Prefer top-level legalName/name; fields.legalName/fields.name are also accepted.
localeNo
legalNameNoLegal company name (required unless name is provided)
projectIdYesDealDesk project id (must match API key / OAuth project)
externalIdNoImmutable business key. Omit to auto-generate local-company-<uuid> (UI default). Not required.
displayNameNoDisplay name (defaults to legalName)
emailDomainsNo
registrationIdNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.5/5.0
Behavior3/5

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

With no annotations, the description must carry behavioral disclosure, and it does add genuine value: externalId is auto-generated as local-company-<uuid> when omitted, and the caller is told not to require fields.externalId. However it says nothing about permissions, conflict/duplicate handling, or mutation side effects.

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?

Three short clauses, front-loaded with the core action, then the field-placement rule, then the externalId caveat. Efficient, though the second and third clauses are really parameter notes rather than the core purpose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 10-parameter creation tool with nested fields, no annotations, and no output schema, the description covers only a fraction of what an agent needs. It should address required-field expectations, what the response contains (e.g., the created id), and duplicate/conflict behavior.

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 only 60%, but the description compensates meaningfully: it explains the name-to-legalName alias, the top-level versus fields placement, and the auto-generation of externalId. The remaining gap is the undocumented params (taxId, locale, emailDomains, registrationId) that neither source explains.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: 'Create a company in the customer directory.' An agent can distinguish this from patch_company/get_company by the create verb, but the description never explicitly names those siblings or contrasts them.

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?

It gives usable guidance on how to call the tool (send legalName or name at the top level) but no guidance on when to use it versus alternatives like create_contact or the various patch tools. Usage is implied by the create verb rather than stated.

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