Skip to main content
Glama
Dynamics 365 MCP Server

Dynamics 365 MCP Server

by Kenny-666

get_record_audit_history

Read-only

Read one page of a Dataverse/Dynamics 365 record's native audit history, preserving paging cookies and audit-setting evidence while withholding attribute values unless explicitly requested.

Instructions

Read one native RetrieveRecordChangeHistory page. Default withholds attribute values. Preserves MoreRecords/cookie and current audit-setting evidence; no actor/time/ID is invented if native AuditRecord is absent. Empty history does not prove logs were deleted or auditing was disabled.

Input Schema

NameRequiredDescriptionDefault
pageSizeNoCompatibility alias for page_size; conflicting values are rejected.
recordIdNoCompatibility alias for record_id; conflicting values are rejected.
page_sizeNoNative audit detail count, default 20.
record_idNo
pageNumberNoCompatibility alias for page_number; conflicting values are rejected.
page_numberNoDefault 1; later pages require the previous native paging_cookie.
maxTextCharsNoCompatibility alias for max_text_chars; conflicting values are rejected.
pagingCookieNoCompatibility alias for paging_cookie; conflicting values are rejected.
includeValuesNoCompatibility alias for include_values; conflicting values are rejected.
paging_cookieNoNative cookie from this same target/page size; maximum 16 KiB UTF-8. No cookie is invented.
collectionNameNoCompatibility alias for collection_name; conflicting values are rejected.
include_valuesNoDefault false. Native audit values are received but withheld from output. Explicit true projects bounded attribute old/new values with heuristic sensitive-field masking.
max_text_charsNoPer-text preview limit, default 2000; truncation is explicit.
collection_nameNo
environment_profileNoOptional named environment profile for this call; omit to use the configured default.

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

A3.7/5.0
Behavior4/5

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

Annotations already cover the read-only, non-destructive profile, so the bar is lower, and the description still adds real behavioral context: values are withheld by default, paging state (MoreRecords/cookie) is preserved, and no actor/time/ID is fabricated when a native AuditRecord is absent. The empty-history warning is a genuinely useful interpretation guard. It stops short of describing output structure or size/truncation behavior in detail.

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?

Four compact sentences, front-loaded with what the tool does, then defaults, then paging guarantees, then the interpretation caveat. The terminology is dense and domain-specific but no sentence is redundant; each contributes a distinct fact.

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 15-parameter paged audit read with no output schema, the description supplies the essential return semantics: page-bounded results, withheld values by default, cookie/MoreRecords preservation, and the absence of invented fields. The main residual gap is that alias behavior and result shape are left to the schema, which is acceptable given its 87% coverage.

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

Parameters3/5

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

Schema description coverage is 87%, so parameters like include_values, paging_cookie, and page_number are already well documented in the schema. The description reinforces the default withholding of attribute values but names no parameters and adds no syntax or alias-handling guidance beyond what the schema states. Baseline 3 applies when the schema carries the load.

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 opens with a specific verb and resource: 'Read one native RetrieveRecordChangeHistory page,' naming the underlying Dataverse message and making the paged-read nature explicit. It does not, however, distinguish this tool from plausible siblings such as get_audit_details or get_change_journal, so an agent cannot route between them from the text alone.

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?

Usage is implied through 'one native ... page' and the paging-cookie retention note, which signals incremental retrieval, and the closing caveat guides interpretation of empty results. There is no explicit when-to-use versus get_audit_details or get_change_journal, and no stated prerequisites such as auditing being enabled or required privileges.

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