Skip to main content
Glama
Sign In

Gloom

by sh.gloom.api
OverviewDiscussionsAdmin

GPU rental price history

gpu.history
Read-onlyIdempotent

Real dated GPU price observations with source and evidence URLs for provider rates. Reference indices are third party, anonymised, with unaltered published values and no public source links. Archived pages are reconstructed, official offer versions are published history, and Azure effective dates remain separate. No interpolated observations. Pro unlocks history; free returns latest preview values regardless of requested dates.

Input Schema

NameRequiredDescriptionDefault
toNo
fromNo
basisNo
limitNo
gpuModelNo
seriesIdNo
includeFractionalNoInclude native fractional GPU counts in effectivePoints. Pro only; observed price history is unchanged.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / from / pattern
      Previous value: -"^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d(?::[0-5]\\d(?:\\.\\d+)?)?(?:Z))$"New value: +"^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d:[0-5]\\d(?:\\.\\d+)?(?:Z))$"
    • changedInput schema / properties / to / pattern
      Previous value: -"^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d(?::[0-5]\\d(?:\\.\\d+)?)?(?:Z))$"New value: +"^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d:[0-5]\\d(?:\\.\\d+)?(?:Z))$"
  2. Changed1 schema field changed
    • addedInput schema / properties / includeFractional
      Added value: +{
+  "description": "Include native fractional GPU counts in effectivePoints. Pro only; observed price history is unchanged.",
+  "type": "boolean"
+}
  3. Changed1 schema field changed
    • changedInput schema / properties / basis / enum
      Previous value: -[
-  "list",
-  "spot",
-  "ask",
-  "reserved"
-]New value: +[
+  "list",
+  "spot",
+  "ask",
+  "reserved",
+  "reference"
+]
  4. Added

TDQS

B3.3/5.0
Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive/openWorld, so safety is covered; the description adds substantive provenance behavior instead: third-party anonymised reference indices with unaltered values and no public source links, reconstructed archived pages, separately-dated Azure effective dates, and no interpolation. The Pro/free gating behavior is also disclosed, which an agent cannot learn from the schema or annotations.

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?

It is compact and front-loads the data-quality statement, with no filler. However, sentences like 'Archived pages are reconstructed, official offer versions are published history, and Azure effective dates remain separate' are telegraphic and ambiguous, forcing re-reading rather than clarifying.

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

Completeness3/5

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

With no output schema, seven parameters at 14% coverage, and a non-trivial data provenance model, the description covers the qualitative side well (provenance, interpolation, tier gating) but leaves the query surface largely unexplained. An agent can understand what the data is but not confidently how to parameterize a request.

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 only 14%: six of seven parameters (from, to, basis, limit, gpuModel, seriesId) have no schema text, and the description compensates only obliquely via 'requested dates' and the reference-index remark. It never explains what basis values mean, how seriesId relates to gpuModel, or how limit interacts with the free-tier preview behavior.

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

Purpose4/5

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

The first sentence names a specific resource and qualifier: dated GPU rental price observations with source and evidence URLs. It is clearly a history/observation feed rather than a board or settle list, but it never names the siblings it differs from (gpu.board, gpu.changes, gpu.settles), so an agent must infer the boundary.

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?

Usage is only implied: it is the tool for dated observations, and the tier note warns that free access returns latest preview values regardless of requested dates, which is a real when-not constraint. There is no explicit statement of when to prefer this over gpu.board or gpu.changes, and no prerequisites for Pro access beyond the gating note.

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

All Gloom 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