Skip to main content
Glama

OutilsIA — Conseiller IA locale

by fr.outilsia
OverviewDiscussionsAdmin

Vérifier un PC pour l'IA locale

check_pc_for_local_ai
Read-only

Estime quels modèles IA locaux conviennent à partir de caractéristiques que l'utilisateur fournit explicitement. Ce n'est pas un scan et l'outil ne doit pas être appelé si CPU, RAM, GPU et VRAM manquent.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
usageNopolyvalent
ram_gbYes
os_nameNo
vram_gbYes
cpu_nameYes
gpu_nameYes
cpu_coresNo
gpu_vendorNo
unified_memoryNo
storage_free_gbNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
decisionYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed8 schema fields changed
    • changedOutput schema / properties / decision / properties / machine / properties / storage_free_gb / type
      Previous value: -"number"New value: +[
+  "number",
+  "null"
+]
    • addedOutput schema / properties / decision / properties / machine / properties / storage_status
      Added value: +{
+  "enum": [
+    "unknown",
+    "measured"
+  ],
+  "type": "string"
+}
    • changedOutput schema / properties / decision / properties / machine / required
      Previous value: -[
-  "cpu",
-  "cpu_cores",
-  "ram_gb",
-  "gpu",
-  "gpu_vendor",
-  "vram_gb",
-  "unified_memory",
-  "storage_free_gb",
-  "os"
-]New value: +[
+  "cpu",
+  "cpu_cores",
+  "ram_gb",
+  "gpu",
+  "gpu_vendor",
+  "vram_gb",
+  "unified_memory",
+  "storage_free_gb",
+  "storage_status",
+  "os"
+]
    • addedOutput schema / properties / decision / properties / purchase / properties / facts_used
      Added value: +{
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}
    • changedOutput schema / properties / decision / properties / purchase / properties / upgrade / anyOf
      Previous value: -[
-  {
-    "additionalProperties": false,
-    "properties": {
-      "guide_url": {
-        "type": "string"
-      },
-      "name": {
-        "type": "string"
-      },
-      "price": {
-        "type": "string"
-      },
-      "summary": {
-        "type": "string"
-      },
-      "target_ram_gb": {
-        "type": "number"
-      },
-      "target_vram_gb": {
-        "type": "number"
-      }
-    },
-    "required": [
-      "name",
-      "summary",
-      "target_vram_gb",
-      "target_ram_gb",
-      "price",
-      "guide_url"
-    ],
-    "type": "object"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "additionalProperties": false,
+    "properties": {
+      "component": {
+        "type": "string"
+      },
+      "guide_url": {
+        "type": "string"
+      },
+      "name": {
+        "type": "string"
+      },
+      "price": {
+        "type": "string"
+      },
+      "summary": {
+        "type": "string"
+      },
+      "target_ram_gb": {
+        "type": "number"
+      },
+      "target_vram_gb": {
+        "type": "number"
+      }
+    },
+    "required": [
+      "name",
+      "summary",
+      "target_vram_gb",
+      "target_ram_gb",
+      "price",
+      "guide_url"
+    ],
+    "type": "object"
+  },
+  {
+    "type": "null"
+  }
+]
    • addedOutput schema / properties / decision / properties / recommended_models / items / properties / estimated
      Added value: +{
+  "type": "boolean"
+}
    • addedOutput schema / properties / decision / properties / recommended_models / items / properties / fit
      Added value: +{
+  "enum": [
+    "full_gpu_fit",
+    "partial_offload",
+    "cpu_offload_heavy",
+    "storage_only",
+    "blocked",
+    "unknown"
+  ],
+  "type": "string"
+}
    • addedOutput schema / properties / decision / properties / recommended_models / items / properties / fit_label
      Added value: +{
+  "type": "string"
+}
  2. First observed

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already indicate readOnlyHint and non-destructive behavior. The description adds useful context beyond that: the tool does not scan the system and relies entirely on explicitly supplied characteristics. This clarifies the tool's boundary without contradicting the annotations.

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?

The description is two succinct sentences with no wasted words. The core function is front-loaded, followed by a clear non-scan caveat and invocation prerequisite.

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?

Given that an output schema exists and annotations cover the safety profile, the description provides enough context for a basic invocation: purpose, required inputs, and a clear exclusion. It could be more complete by explaining how optional parameters like usage affect the estimation, but this is not critical for core usage.

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

Parameters2/5

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

Schema description coverage is 0%, so the description carries the burden of explaining parameters. It names the four required hardware characteristics (CPU, RAM, GPU, VRAM) but does not add meaning for the six optional parameters such as usage, os_name, unified_memory, or storage_free_gb. This leaves the agent with limited semantic guidance beyond raw schema names.

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 that the tool estimates which local AI models are suitable based on user-provided hardware characteristics. It uses a specific verb ('Estime quels modèles IA locaux conviennent') and explicitly distinguishes itself from a scan, which helps separate it from sibling tools like lookup_local_model or list_models_for_budget.

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 gives clear when-not-to-use guidance: it is not a scan and must not be called when CPU, RAM, GPU, or VRAM are missing. It does not explicitly name alternative tools, but the exclusion and prerequisite are strong enough to guide invocation.

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

All OutilsIA — Conseiller IA locale 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