Skip to main content
Glama

mcp-knowledge

by io.github.getgapup
OverviewDiscussionsAdmin

process_mapping

Read-only

Mapping des process opérationnels — Gapup agent-payable C-suite expertise (COO). Returns a structured, audited deliverable. Reference case: Decathlon France — process Retour produit en magasin · 1700 magasins · 200 retours/j/magasin · -30 à -50% temps cible. Inputs are validated server-side — send the documented case fields.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
asyncNoIf true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
focusNo
companyYes
processesYes
presenterScriptNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed8 schema fields changed
    • addedInput schema / properties / company / properties
      Added value: +{
+  "fte": {
+    "minimum": 1,
+    "type": "integer"
+  },
+  "locations": {
+    "minimum": 1,
+    "type": "integer"
+  },
+  "name": {
+    "maxLength": 120,
+    "minLength": 2,
+    "type": "string"
+  },
+  "sector": {
+    "maxLength": 120,
+    "minLength": 2,
+    "type": "string"
+  },
+  "toolStack": {
+    "items": {
+      "type": "string"
+    },
+    "maxItems": 30,
+    "type": "array"
+  }
+}
    • addedInput schema / properties / company / required
      Added value: +[
+  "name",
+  "sector",
+  "fte"
+]
    • addedInput schema / properties / focus / maxLength
      Added value: +400
    • addedInput schema / properties / presenterScript
      Added value: +{
+  "items": {
+    "properties": {
+      "durationSec": {
+        "maximum": 120,
+        "minimum": 15,
+        "type": "number"
+      },
+      "keyPointsToAcknowledge": {
+        "items": {
+          "maxLength": 200,
+          "minLength": 5,
+          "type": "string"
+        },
+        "maxItems": 5,
+        "type": "array"
+      },
+      "motionHint": {
+        "enum": [
+          "opening-confidence",
+          "explaining",
+          "pointing-at-chart",
+          "thoughtful-pause",
+          "emphatic-point",
+          "nodding-listening",
+          "hand-gesture-open",
+          "summary-pose",
+          "closing-confidence"
+        ],
+        "type": "string"
+      },
+      "narration": {
+        "maxLength": 1200,
+        "minLength": 80,
+        "type": "string"
+      },
+      "slideId": {
+        "maxLength": 60,
+        "minLength": 2,
+        "type": "string"
+      },
+      "slideTitle": {
+        "maxLength": 120,
+        "minLength": 3,
+        "type": "string"
+      }
+    },
+    "required": [
+      "slideId",
+      "slideTitle",
+      "narration",
+      "durationSec"
+    ],
+    "type": "object"
+  },
+  "maxItems": 15,
+  "minItems": 6,
+  "type": "array"
+}
    • addedInput schema / properties / processes / items
      Added value: +{
+  "properties": {
+    "currentPainPoints": {
+      "maxLength": 500,
+      "minLength": 10,
+      "type": "string"
+    },
+    "description": {
+      "maxLength": 400,
+      "minLength": 20,
+      "type": "string"
+    },
+    "estimatedVolumePerDay": {
+      "minimum": 0,
+      "type": "number"
+    },
+    "processId": {
+      "maxLength": 80,
+      "minLength": 2,
+      "type": "string"
+    },
+    "processName": {
+      "maxLength": 160,
+      "minLength": 4,
+      "type": "string"
+    }
+  },
+  "required": [
+    "processId",
+    "processName",
+    "description"
+  ],
+  "type": "object"
+}
    • addedInput schema / properties / processes / maxItems
      Added value: +8
    • addedInput schema / properties / processes / minItems
      Added value: +1
    • addedInput schema / required
      Added value: +[
+  "company",
+  "processes"
+]
  2. First observed

TDQS

C2.3/5.0
Behavior3/5

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

Annotations already indicate readOnlyHint=true and openWorldHint=true. The description adds that inputs are validated server-side and that a structured, audited deliverable is returned, which is useful context but does not mention async behavior or what 'audited' entails despite an async parameter.

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

Conciseness3/5

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

The description is relatively short but includes unnecessary marketing fluff ('Gapup agent-payable C-suite expertise (COO)') and a verbose reference case. It is not front-loaded with the most essential operational details, though it is not excessively long.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, complex nested input parameters (company, processes, presenterScript), and no description of return values, the tool description is far too incomplete. An agent would not know what the deliverable looks like or how to properly structure the input, making it nearly impossible to invoke correctly.

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

Parameters1/5

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

Schema description coverage is only 20% (only the async parameter has a description). The tool description does not explain company, processes, focus, or presenterScript, and merely says 'send the documented case fields' without specifying what those are. This is a severe gap for an agent to construct valid input.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states 'Mapping des process opérationnels' and mentions it returns a structured, audited deliverable, which conveys a process mapping purpose. However, it lacks a clear verb (e.g., 'analyze', 'create') and does not distinguish itself from the similar sibling 'process_mining'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance on when to use this tool versus alternatives. The Decathlon reference case is an example of use but not a directive or comparison to process_mining or other process-related tools.

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

All mcp-knowledge toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources