Skip to main content
Glama

What changed since your knowledge cutoff

what_changed_since
Read-onlyIdempotent

Call this when a user asks about current prices, models or retirements and your knowledge may be out of date: give the date your knowledge ends (YYYY-MM-DD) and get everything recorded since, grouped: new models and plans, price changes (old to new, percent, date first seen, source URL), retirements a provider's own lifecycle page dates (effective, and scheduled ones still ahead), and removed plans. kind=llm (LLM API models and inference hosts), gpu, vps or all. counts are for the whole period; each group lists at most limit entries and, when cut, says so and links the full CSV; summary is a one-line answer. gaps names the days with no data and the sources that are stopped now (never filled in); record_begins and notice say how far back the record goes. Entries carry recorded values only, never a current price: use search_skus or get_price for today's price. Returns an error object for a bad or future date. Retirements come from Azure VM and AWS Bedrock lifecycle pages only (other providers are not parsed). Same answer as GET /v1/since and the page /prices/since/. To page through every entry or filter by category use changes_since. Robots.txt changes of AI crawlers are a separate dataset (related.robots_txt_policy_changes, tool crawlers_changes).

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "date": "<date>"
    },
    "name": "what_changed_since"
  }
}

Input Schema

NameRequiredDescriptionDefault
dateYesUTC date, YYYY-MM-DD: the day your knowledge ends, e.g. 2026-06-01
kindNoall (default), llm (LLM API models and inference hosts), gpu or vpsall
limitNoEntries per group, 1 to 200
providerNoProvider slug, e.g. openai, hetzner

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already declare a safe idempotent read, so the description's value is in the details it adds: counts cover the whole period while each group is capped at `limit` and self-declares truncation with a full-CSV link, `gaps` names days with no data and permanently stopped sources, `record_begins`/`notice` bound the record's history, and a bad or future date returns an error object. It also discloses a real coverage limitation — retirements come only from Azure VM and AWS Bedrock lifecycle pages — which an agent could otherwise never learn.

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 usage trigger is correctly front-loaded, and nearly every clause carries information, but it is delivered as one dense run-on paragraph with parenthetical lists nested three deep. A reader must parse the whole block to find the coverage caveat (Azure/AWS-only retirements) and the error behavior, which deserve their own sentences.

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 four-parameter reporting tool with no output schema, the description fully previews the response shape (grouped sections, per-group counts, `gaps`, `record_begins`, `notice`, CSV link) and closes the obvious failure modes (bad/future date, historical vs current price). Nothing an agent needs in order to call it and interpret the result is missing.

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

Parameters5/5

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

Schema coverage is 100%, so the schema carries the baseline, but the description adds meaning the schema does not: `limit` is per-group rather than total, with an explicit truncation notice and CSV fallback, and `date` is reframed as 'the day your knowledge ends' with future dates rejected. The `kind` semantics (llm = LLM API models and inference hosts) and the period-wide counts clarify how results are sliced.

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 verb and resource — returns everything recorded since the date the agent's knowledge ends — and immediately names what it is not: entries carry recorded values only, and search_skus/get_price must be used for today's price. The grouping vocabulary (new models, price changes, retirements, removed plans) makes it distinguishable from changes_since and get_history without opening any schema.

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

Usage Guidelines5/5

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

Opens with an explicit trigger: 'Call this when a user asks about current prices, models or retirements and your knowledge may be out of date.' It names alternatives with the condition that selects them — changes_since for paging or category filtering, search_skus/get_price for today's price, crawlers_changes for robots.txt data — which is exactly the routing info an agent needs.

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.

Resources