Skip to main content
Glama

Lantern Works GPU Prices: daily GPU rental price comparison

get_price_changes

Read-only

GPU rental price changes among tracked providers, each with old/new hourly price, change_pct, direction, the vendor source_url, a stable event_id (dedupe key) and rate_id. Marketplace median moves also have composition_flag (composition, price, mixed, unknown, or null) from successive median, minimum and listing count; composition, mixed and unknown are not price moves.

since: 'YYYY-MM-DD' returns every change on or after that date, newest first (daily snapshots in /api/v1/gpu-prices/history.json); omitted returns the latest day's moves (/api/v1/gpu-price-changes.json). cursor: pass next_cursor from a previous call to get every change after it, oldest first, with has_more; loop until has_more is false, and store next_cursor only after processing (a watcher never misses or repeats events). error cursor_expired means re-sync with since and dedupe by event_id. kinds: optional subset of down, up, new, removed, same. gpu: optional model filter (substring, e.g. 'H100'). limit 1-200. Includes data_checked_at and next_refresh_utc (prices refresh daily at about 10:23 UTC).

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "get_price_changes"
  }
}

Input Schema

NameRequiredDescriptionDefault
gpuNo
modeNofull
kindsNo
limitNo
sinceNo
cursorNo

Output Schema

NameRequiredDescriptionDefault
okYes
modeNo
errorNo
changesNo
has_moreNo
last_seqNo
next_cursorNo
referral_disclosureNoOne-line referral disclosure, present whenever the result names a provider; each provider-naming item then has tracked_url (tagged /go/ redirect).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changed
    • addedOutput schema / properties / changes / items / properties / composition_flag
      Added value: +{
      +  "enum": [
      +    "composition",
      +    "price",
      +    "mixed",
      +    "unknown",
      +    null
      +  ],
      +  "type": [
      +    "string",
      +    "null"
      +  ]
      +}
    • addedOutput schema / properties / changes / items / properties / lowest_offer_usd
      Added value: +{
      +  "type": [
      +    "number",
      +    "null"
      +  ]
      +}
    • addedOutput schema / properties / changes / items / properties / offer_count
      Added value: +{
      +  "minimum": 0,
      +  "type": [
      +    "integer",
      +    "null"
      +  ]
      +}
    • addedOutput schema / properties / changes / items / properties / previous_lowest_offer_usd
      Added value: +{
      +  "type": [
      +    "number",
      +    "null"
      +  ]
      +}
    • addedOutput schema / properties / changes / items / properties / previous_offer_count
      Added value: +{
      +  "minimum": 0,
      +  "type": [
      +    "integer",
      +    "null"
      +  ]
      +}
  2. Changed2 schema fields changed
    • addedOutput schema / properties / changes / items / properties / gap_days
      Added value: +{
      +  "minimum": 0,
      +  "type": [
      +    "number",
      +    "null"
      +  ]
      +}
    • addedOutput schema / properties / changes / items / properties / last_verified_before
      Added value: +{
      +  "format": "date-time",
      +  "type": [
      +    "string",
      +    "null"
      +  ]
      +}
  3. Changed1 schema field changed
    • addedOutput schema / properties / referral_disclosure
      Added value: +{
      +  "description": "One-line referral disclosure, present whenever the result names a provider; each provider-naming item then has tracked_url (tagged /go/ redirect).",
      +  "type": "string"
      +}
  4. Changed1 schema field changed
    • addedInput schema / additionalProperties
      Added value: +false
  5. Changed7 schema fields changed
    • addedInput schema / properties / cursor
      Added value: +{
      +  "default": null,
      +  "type": "string"
      +}
    • addedInput schema / properties / kinds
      Added value: +{
      +  "default": null,
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
    • addedOutput schema / properties / changes / items / properties
      Added value: +{
      +  "event_id": {
      +    "type": [
      +      "string",
      +      "null"
      +    ]
      +  },
      +  "key": {
      +    "type": [
      +      "string",
      +      "null"
      +    ]
      +  },
      +  "rate_id": {
      +    "type": [
      +      "string",
      +      "null"
      +    ]
      +  },
      +  "seq": {
      +    "type": [
      +      "integer",
      +      "null"
      +    ]
      +  },
      +  "snapshot_id": {
      +    "type": [
      +      "string",
      +      "null"
      +    ]
      +  }
      +}
    • changedOutput schema / properties / error / properties / code / enum
      Previous value: -[
      -  "invalid_argument",
      -  "invalid_cursor",
      -  "not_found",
      -  "feed_unavailable",
      -  "feed_invalid",
      -  "upstream_unavailable",
      -  "internal_error"
      -]New value: +[
      +  "invalid_argument",
      +  "invalid_cursor",
      +  "cursor_expired",
      +  "not_found",
      +  "feed_unavailable",
      +  "feed_invalid",
      +  "upstream_unavailable",
      +  "internal_error"
      +]
    • addedOutput schema / properties / has_more
      Added value: +{
      +  "type": [
      +    "boolean",
      +    "null"
      +  ]
      +}
    • addedOutput schema / properties / last_seq
      Added value: +{
      +  "type": [
      +    "integer",
      +    "null"
      +  ]
      +}
    • addedOutput schema / properties / next_cursor
      Added value: +{
      +  "type": [
      +    "string",
      +    "null"
      +  ]
      +}
  6. First observed

TDQS

A4.3/5.0
Behavior5/5

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

With readOnlyHint/openWorldHint already covering safety, the description adds substantial behavioral context beyond annotations: a stable event_id dedupe key, ordering guarantees (newest-first for since, oldest-first for cursor), the rule to persist next_cursor only after processing so a watcher never misses or repeats events, the cursor_expired error contract, and a refresh cadence of roughly 10:23 UTC daily. It also warns that composition/mixed/unknown values are not real price moves, which prevents a costly misinterpretation.

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?

Content is front-loaded — the resource and payload come first, then parameter behavior in the order an agent would consider it. It is dense and runs long, and some of the return-field detail is arguably redundant given an output schema exists, but nearly every sentence conveys a distinct operational rule.

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?

For a six-parameter read tool with an output schema and read-only annotations, the description is complete enough to call correctly on the first try: mode selection, pagination loop, error recovery, filtering and freshness are all covered. The only material omission is the undocumented 'mode' parameter.

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 description coverage is 0%, so the description carries the full burden, and it explains since, cursor, kinds, gpu (substring, with an example) and limit meaningfully. However, the 'mode' parameter (default 'full') is never mentioned in the description or schema, leaving one of six parameters with no semantics at all.

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 clause names a specific verb and resource — 'GPU rental price changes among tracked providers' — and lists the per-event fields returned, so an agent knows exactly what this returns. It does not name or contrast any sibling (e.g., compare_gpu_prices, watch_price), so it falls short of the top mark for differentiation.

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?

It gives concrete conditional guidance between the two retrieval modes: omit 'since' for the latest day's moves, supply 'since' for a full backfill, and use 'cursor' to page forward — plus the loop-until-has_more-false rule and the cursor_expired recovery path. What is missing is guidance on when to reach for this tool versus related tools like watch_price or compare_gpu_prices.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.