ALM X++ MCP Server

erp_read_session

Read-onlyIdempotent

WHEN: to READ from the ERP through form tools, where several calls must share ONE ERP session: open a form, filter its grid, read its values. Each separate erp_read / erp_call starts a new ERP session, so a form opened by one call is gone at the next; this tool runs the steps in order in a single session. Every step must be a read-only tool (opening, filtering, selecting, reading); it refuses the whole call, before running anything, if one step could change data. It stops at the first step that fails. stepsJson: [{"tool":"form_open_menu_item","arguments":{...}}, ...], at most 15 steps. Close the forms you open as the last step.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "instance": "<instance>",
      "stepsJson": "<stepsJson>"
    },
    "name": "erp_read_session"
  }
}

Input Schema

Name	Required	Description	Default
`instance`	Yes	Instance alias from erp_list_instances.
`stepsJson`	Yes	JSON array of steps: [{"tool":"<name from erp_list_tools>","arguments":{...}}].

Schema Changelog

Changes observed during successful MCP inspections.

AddedOct 29, 2026

TDQS

A4.6/5.0

Behavior4/5

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

Beyond the annotations (readOnlyHint, idempotentHint, destructiveHint=false), the description discloses non-obvious behavior: whole-call validation before any step runs, fail-fast on first error, and a 15-step cap. It does not describe how results or errors are surfaced per step, which is the remaining behavioral gap since there is no output schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

It is front-loaded with 'WHEN:' and every subsequent sentence adds a distinct constraint (session sharing, read-only enforcement, fail-fast, step format, step cap, cleanup). No filler or restatement of the title.

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 two-parameter orchestrator with no output schema, the description covers invocation, constraints, and error semantics well. The only shortfall is that it never indicates what the caller gets back (per-step results vs. a single aggregated result), which matters for a batch-style 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 coverage is already 100% for both params, and the description adds real value on top: a concrete step shape with a worked example ('{"tool":"form_open_menu_item","arguments":{...}}'), the constraint that each step's tool must be a read-only form tool, and the 15-step limit. The 'instance' param is left to the schema, which is acceptable.

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 specific verb and resource ('READ from the ERP through form tools') and immediately scopes it to the multi-step single-session case. It explicitly contrasts with erp_read / erp_call, so an agent can pick the right tool without inspecting schemas.

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?

The 'WHEN' framing plus the explanation that erp_read / erp_call each start a fresh session gives a concrete selection rule. It also states operational exclusions: every step must be read-only, the whole call is refused pre-flight if any step could mutate, execution stops at the first failure, and forms should be closed in the last step.

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 tools Inspect

Try in Browser

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.