Skip to main content
Glama
Dynamics 365 MCP Server

Dynamics 365 MCP Server

by Kenny-666

call_d365_api_action

Destructive

Invoke CSDL-defined Dynamics 365 Actions or Functions after typed validation, with entity binding and parameters. Use dry_run previews and planHash checks before execution.

Instructions

Invoke a current CSDL-defined Action/Function after typed validation. Preserves legacy defaults: Action POST and immediate execution, returning native data directly. Supports single-entity or collection binding, explicit overload IDs, primitive/enum/structural collections and safe Function parameter aliases. Optional dry_run previews without invocation and withholds parameter values by default. Optional expected_hash checks preview planHash; return_details=true returns receipt/data. No Action replay or generic business readback.

Input Schema

NameRequiredDescriptionDefault
dryRunNoDefault false preserves immediate legacy invocation. True performs metadata reads/validation only.
bindingNo
dry_runNoDefault false preserves immediate legacy invocation. True performs metadata reads/validation only.
actionNameNoExact case-sensitive native operation/import name or qualified name, never a URL/path.
isFunctionNoInvocation defaults false (Action); discovery omits this to inspect both kinds.
parametersNoExact case-sensitive non-binding parameter names. Int64 and Decimal support exact strings; no navigation/deep-insert properties.
action_nameNoExact case-sensitive native operation/import name or qualified name, never a URL/path.
is_functionNoInvocation defaults false (Action); discovery omits this to inspect both kinds.
signatureIdNoAdvertised get_api_operation signature ID; required to disambiguate matching overloads.
expectedHashNoOptional current preview planHash; detects changed metadata/target/arguments, not concurrent record changes.
signature_idNoAdvertised get_api_operation signature ID; required to disambiguate matching overloads.
expected_hashNoOptional current preview planHash; detects changed metadata/target/arguments, not concurrent record changes.
returnDetailsNoDefault false returns native data directly; true wraps receipt, HTTP status and data.
return_detailsNoDefault false returns native data directly; true wraps receipt, HTTP status and data.
environment_profileNoOptional named environment profile for this call; omit to use the configured default.
includeParameterValuesNoExplicit preview opt-in to show plaintext normalized values and Function URL; default false.
include_parameter_valuesNoExplicit preview opt-in to show plaintext normalized values and Function URL; default false.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.1.2
    • addedInput schema / properties / environment_profile
      Added value: +{
      +  "description": "Optional named environment profile for this call; omit to use the configured default.",
      +  "pattern": "^[A-Za-z][A-Za-z0-9_]{0,31}$",
      +  "type": "string"
      +}
  2. First observedv1.0.0

TDQS

A4.3/5.0
Behavior4/5

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

The annotations already declare non-readOnly, non-idempotent and destructive, and the description adds real value on top: immediate execution by default, preview-without-invocation, parameter values withheld unless explicitly opted in, receipt-wrapping via return_details, and the crucial caveat that expected_hash detects changed metadata/target/arguments but not concurrent record changes. It does not discuss permissions or what an arbitrary Action may mutate, which is the main remaining behavioral gap.

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?

It is front-loaded with the core action and keeps each sentence carrying distinct information (defaults, binding support, preview, hash check, exclusions). Some sentences are dense, alias-laden jargon ('safe Function parameter aliases') that costs more parsing effort than it returns, but there is little outright waste.

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 17-parameter destructive invocation tool with no output schema, the description covers invocation defaults, preview/dry-run behavior, return shapes, overload disambiguation and explicit non-capabilities. Missing pieces are authorization prerequisites and any hint about what side effects a caller should expect, which matter for a destructiveHint=true tool.

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 description coverage is 94%, so the baseline is 3; the description still adds meaning by explaining the legacy default polarity (Action POST / immediate execution), the dry_run vs expected_hash interplay, the aliasing story ('safe Function parameter aliases'), and supported parameter shapes (primitive/enum/structural collections, single-entity vs collection binding). It does not explain the includeParameterValues or environment_profile parameters beyond what the schema already says.

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 description gives a specific verb and resource ('Invoke a current CSDL-defined Action/Function') plus execution semantics ('Action POST and immediate execution, returning native data directly'). It also distinguishes the tool from discovery siblings by referencing 'Advertised get_api_operation signature ID', so an agent can tell it is the execution step rather than a metadata 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 clear when-to-use context for the optional modes (dry_run previews without invocation, expected_hash verifies a preview planHash, return_details wraps a receipt) and states exclusions ('No Action replay or generic business readback'). It stops short of naming competing record-level siblings like create_new_record or query_by_odata and saying when those are preferable, but the operation-vs-data distinction is implied.

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