Skip to main content
Glama

d365fo_file

Destructive

Create, modify, delete, or generate Dynamics 365 F&O AOT objects (classes, tables, forms) as XML files, handling model prefixes, project registration, and extension operations like adding methods or fields.

Instructions

Create, modify, delete, or generate a D365FO AOT object. Choose an action: • create → write a NEW object file into PackagesLocalDirectory (UTF-8 BOM, auto-added to .rnrproj). THE WRITE STEP — incomplete until isError=false; ⚠️/❌ = failure. Extensions: objectName="Base.PrefixExtension". • modify → edit an EXISTING object. APPLIES IMMEDIATELY, no dry-run — confirm with the user first; revert with undo_last_modification. Needs operation. • delete → remove an object's XML from disk AND un-register it from every .rnrproj of the model that lists it. IRREVERSIBLE — confirm with the user first. Reports ❌ when the object is not found, never a silent no-op. • generate → XML as TEXT only, no write (Azure/Linux fallback). Try create first. create/modify/delete need Windows. 📖 Parameters are NOT inlined here: get_knowledge(kind="op-spec", topic=""|"") returns the contract for the one you picked — pass its values nested in params (modify) / properties (create), along with any packageName/packagePath/solutionPath/workspacePath override. Model + prefix auto-applied. Classes: member vars inside the class { }, methods after the closing }.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
actionYesOne of the four modes described above.
paramsNo[modify] Operation-specific parameters as ONE nested object, per get_knowledge(kind="op-spec", topic="<operation>"). A missing/wrong one returns that COMPLETE spec — follow it, do not guess.
filePathNo[modify|delete] Absolute XML path — bypasses symbol-DB lookup. Use for objects just created.
modelNameNoTarget model — auto-detected. NEVER take it from search results (those are source models).
operationNo[modify] REQUIRED unless using operations[]. add-method also UPDATES in place; replace-code is the surgical oldCode→newCode path.
overwriteNoAllow overwriting — never rewrite via PowerShell.
objectNameNoBase name WITHOUT model prefix — the tool prepends it. Extension classes: "{Base}_Extension". NEVER hand-build the prefix.
objectTypeNoEach security/menu-item type is its own AOT folder — NEVER use security-privilege for duty or role. [modify]/[generate] cover the core families + their *-extension variants; [delete] takes the same enum as [create].
operationsNo[modify|create] PREFERRED for 2+ edits to the SAME object — ONE call, not one per edit. On create they run against the just-created object, under the name it actually got. Entries are {operation, …op-spec params}; objectType/objectName/modelName stay top-level. Applied in order, stopped at the first failure, per-operation results back.
propertiesNo[create] Per-objectType creation properties (label, fields[], extends, enumValues[], primaryTable, …) — NOT in this schema. Fetch yours: get_knowledge(kind="op-spec", topic="<objectType>").
sourceCodeNoX++ source. FOR CLASSES auto-split: <Declaration> = class line + member vars; <Methods> = each method after the closing }.
xmlContentNoComplete XML written verbatim (+overwrite=true rewrites an object).
projectPathNoPath to .rnrproj (auto-detected).
addToProjectNoAdd to the ACTIVE .rnrproj — keep the default.
createBackupNo[modify] Back up before modifying.
groundingTokenNoFrom prepare(change/create). Required for *-extension when GROUNDING_ENFORCE=true; object-bound.
Behavior4/5

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

Annotations already mark destructiveHint=true, and the description adds crucial specifics: modify applies immediately with no dry-run, delete is irreversible and reports ❌ when not found (never silent no-op), and create is incomplete until isError=false. It also notes .rnrproj registration handling. No contradiction with annotations.

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?

The description is long but tightly structured with bullet points per action and clear warnings. It front-loads the primary actions and then details parameter relationships. It could trim some repetition (e.g., 'confirm with the user first' appears twice) but remains focused.

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 complex tool with 16 parameters and 4 actions, the description covers the core workflow, parameter dependencies (op-spec lookup), and behavioral caveats (irreversibility, Windows requirement, extension naming). It doesn't explain return values but has no output schema, so that's not required. Minor gaps: specific error handling beyond 'isError=false' and interaction with workspace paths could be more explicit, but adequate.

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 has 100% coverage, but the description adds meaning beyond it: modelName must never come from search results, objectName should never have prefix hand-built, operations array preferred for batch edits with order and failure handling, and properties/params require get_knowledge. These nuances aren't in the schema.

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 clearly states four specific actions (create, modify, delete, generate) acting on a D365FO AOT object, and distinguishes each with distinct semantics. It explicitly mentions writing into PackagesLocalDirectory for create and XML text for generate, making it distinct from sibling tools like get_object_info or search.

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?

Provides explicit when-to-use guidance: generate as an Azure/Linux fallback ('try create first'), Windows requirement for create/modify/delete, confirmation needed for modify (immediate apply) and delete (irreversible), and pointer to get_knowledge for operation-specific contracts. It also references undo_last_modification as a revert path.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/dynamics365ninja/d365fo-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server