Skip to main content
Glama

ALM X++ MCP Server

by io.github.alimbenhelal-pro

appinsights_diagnose_slowness

WHEN: user wants to understand/deduce why a D365 F&O environment feels slow, using the real Application Insights telemetry the environment already emits -- no trace file upload needed. Runs a set of canned KQL queries and assembles one combined report:

  1. X++ exception hotspots (exceptions table) -- top types/messages by count.

  2. Hot custom telemetry events (customEvents table) -- top event names by frequency, plus a duration breakdown for events that carry an ElapsedMilliseconds custom property (covers ALMMonitoring-instrumented FDDs, and any out-of-box signal using the same convention).

  3. Slow web requests/dependencies (requests/dependencies tables) -- only rendered if the workspace actually has data there (uncommon for FnO's own AOS tier, but present for Commerce/Portal/custom web extensions sharing the same App Insights resource). Requires the connection to be configured first via appinsights_set_connection (or server env vars).

Triggers: 'déduire et comprendre les lenteurs', 'why is my environment slow', 'diagnose slowness from App Insights', 'analyse la lenteur avec App Insights', 'performance issue live environment', 'slow environment telemetry'.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
topNoMax rows per section (1-50). Default 15.
lookbackHoursNoHow far back to analyze, in hours (1-720). Default 24.
minDurationMsNoMinimum average duration (ms) for a custom event to be flagged as 'slow'. Default 2000.

TDQS

A4.1/5.0
Behavior4/5

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

With no annotations provided, the description carries the behavioral disclosure burden and does it reasonably well. It explains that the tool runs canned KQL queries, assembles a combined report, conditionally renders sections based on data availability, and requires a configured connection. It does not address potential runtime cost or error behavior, but for a diagnostic read tool the disclosed behavior is sufficient.

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 longer than average but well structured: it front-loads the WHEN scenario, then lists the report contents in an easy-to-scan numbered format, and ends with trigger phrases. The trigger list is somewhat redundant with the opening WHEN, but it helps with invocation matching and does not feel like padding.

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 tool with no output schema, the description compensates by detailing the three sections the report will contain and their conditional rendering. It also states the required connection prerequisite and the parameters are fully documented in the schema. The only small gap is the lack of explicit behavior when no connection has been configured, but the prerequisite is already stated.

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?

The input schema covers all three parameters with descriptions, defaults, and valid ranges, so the description does not need to add much. The report description slightly reinforces the role of minDurationMs and top, but overall the parameters are already fully documented 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 opens with a clear WHEN statement and defines the tool as diagnosing why a D365 F&O environment is slow using existing Application Insights telemetry, with no trace upload. It enumerates exactly what the combined report contains, making its purpose concrete and distinguishable from generic App Insights query tools.

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?

The description explicitly states when to use it: when the user wants to understand slowness from App Insights telemetry. It also names the prerequisite of configuring the connection via appinsights_set_connection or server env vars. However, it does not explicitly contrast itself with sibling tools like appinsights_query or detect_performance_issues, leaving alternatives implicit.

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

All ALM X++ MCP Server toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.1/5.0
Disambiguation4/5

Most tools have distinct purposes and clear triggers, reducing ambiguity. For example, PR-related tools are separated into analysis, listing, commenting, and dependency mapping. However, some overlap exists between find_references, find_extensions, and find_callers, which could confuse an agent without careful descriptions.

Naming Consistency4/5

Tool names follow a consistent snake_case pattern with verb_noun structure within subgroups (e.g., ado_*, find_*, search_*, generate_*). There is no mixing of camelCase or other styles, though the variety of prefixes slightly reduces predictability.

Tool Count3/5

With 38 tools, the server feels slightly over-scoped for its domain. While each tool has a specific function, the number is high compared to typical well-scoped servers (10-15 tools). Some tools like find_references and find_callers could be consolidated.

Completeness4/5

The tool set covers a broad range of D365 F&O development and DevOps tasks, including code search, analysis, security, performance, upgrades, and work item management. Minor gaps exist, such as the absence of direct object modification or batch job management, but the core workflows are well covered.

Resources