Skip to main content
Glama

corpusAI Cloud Pricing

by io.github.JTraversa
OverviewDiscussionsAdmin

GPU rental index

gpu_index
Read-onlyIdempotent

Paid (0.05 USDC per call). Daily USD per GPU-hour index per provider and market for one GPU model, with hyperscaler spot legs. For each snapshot day and (provider, market): number of quotes and the lowest, median, mean and highest USD per GPU-hour. Rows with provider aws-spot or gcp-spot are computed from our own spot price events for the instance family that carries the GPU (time-weighted daily bar divided by GPUs per node, per region), so the neo-cloud market and hyperscaler spot are comparable in one series. Quote history starts 2026-09-13; hyperscaler spot legs reach back to the start of our event data.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
toNoLast day (inclusive), YYYY-MM-DD. Default: latest.
gpuYesNormalized GPU model from /gpu/models. Example: H100 SXM
fromNoFirst day (inclusive), YYYY-MM-DD. Default: earliest.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
gpuNo
noteNo
countNo
seriesNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": true,
+  "properties": {
+    "count": {
+      "type": "number"
+    },
+    "gpu": {
+      "type": "string"
+    },
+    "note": {
+      "type": "string"
+    },
+    "series": {
+      "items": {
+        "additionalProperties": true,
+        "properties": {
+          "day": {
+            "type": "string"
+          },
+          "gpus": {
+            "description": "Hyperscaler legs only: GPUs per node.",
+            "type": "number"
+          },
+          "hi": {
+            "type": "number"
+          },
+          "instance": {
+            "description": "Hyperscaler legs only.",
+            "type": "string"
+          },
+          "lo": {
+            "type": "number"
+          },
+          "market": {
+            "type": "string"
+          },
+          "mean": {
+            "type": "number"
+          },
+          "median": {
+            "type": "number"
+          },
+          "n": {
+            "description": "Quotes behind the row (1 for hyperscaler legs).",
+            "type": "number"
+          },
+          "provider": {
+            "description": "A quote provider, or `aws-spot` / `gcp-spot` for legs from our own events.",
+            "type": "string"
+          },
+          "region": {
+            "description": "Hyperscaler legs only.",
+            "type": "string"
+          }
+        },
+        "required": [
+          "day",
+          "provider",
+          "market",
+          "n",
+          "lo",
+          "median"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    }
+  },
+  "type": "object"
+}
  2. Changed1 schema field changed
    • changedInput schema / properties / gpu / description
      Previous value: -"Normalised GPU model from /gpu/models. Example: H100 SXM"New value: +"Normalized GPU model from /gpu/models. Example: H100 SXM"
  3. Changed1 schema field changed
    • changedInput schema / properties / gpu / description
      Previous value: -"Normalized GPU model from /gpu/models. Example: H100 SXM"New value: +"Normalised GPU model from /gpu/models. Example: H100 SXM"
  4. Changed1 schema field changed
    • changedInput schema / properties / gpu / description
      Previous value: -"Normalised GPU model from /gpu/models. Example: H100 SXM"New value: +"Normalized GPU model from /gpu/models. Example: H100 SXM"
  5. First observed

TDQS

A4.2/5.0
Behavior5/5

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

Annotations already declare readOnly, idempotent, non-destructive behavior, yet the description adds substantial extra context: a per-call price (0.05 USDC), the provenance/methodology for aws-spot and gcp-spot rows (time-weighted daily bar divided by GPUs per node per region), and data coverage start dates. This is exactly the value-add expected beyond structured fields.

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?

Front-loaded with cost, purpose and scope, and every subsequent sentence carries real information (aggregation outputs, spot methodology, date ranges). It runs long, but there is little filler to cut.

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

Completeness5/5

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

With an output schema present, the description need not spell out return values, and it instead supplies the pricing, comparability rationale, and coverage windows an agent needs to call the tool correctly. Nothing material is missing.

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?

Schema description coverage is 100%, so gpu normalization, date format, and from/to defaults are already fully documented in the schema. The description adds indirect context (one model at a time, data availability windows) but no new parameter-level syntax or constraints, so the baseline 3 applies.

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?

States a specific resource (daily USD/GPU-hour index), scope (one GPU model, per provider and market), and includes the hyperscaler spot legs. It is precise enough that an agent can distinguish it from gpu_quotes or index_history without opening schemas.

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

Usage Guidelines3/5

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

The description establishes context (paid per call, quote history start dates, spot legs reach further back) but never says when to use this tool versus siblings like gpu_quotes or index_fixing, and gives no explicit exclusions. Usage is implied rather than stated.

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

All corpusAI Cloud Pricing 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