Skip to main content
Glama

Upstream

by io.github.toolweather
OverviewDiscussionsAdmin

What changed recently in AI/dev APIs?

list_recent_api_changes
Read-onlyIdempotent

List the on-demand feed of recent AI and developer API changes (status flips, deprecation-page edits, model retirements, pricing-page edits). Use for a chosen window, one provider, or one kind, when explaining sudden breakage. Not for live up/down (check_api_status) and not for the once-a-day digest, which also covers MCP server breakage (get_digest). Returns summary, count, freshness, and changes[] with provider, kind, title, detail, source, and at, newest first. Status rows arrive within about 5 minutes; doc-page rows every few hours. A limit above 500 is clamped to 500; an unknown provider returns an empty list, not an error. Example: {"provider":"anthropic","kind":"model_retirement"}. Free within the daily quota, then $0.01 via x402. Alias: get_changes.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
kindNoOptional type filter. status = provider state flips; deprecations = deprecation-page line edits; model_retirement = a model id became deprecated or retired; pricing = pricing-page line edits. Omit for all four.
limitNoHow many changes to return, newest first. Positive integer. Omit for 100.
sinceNoExclusive lower bound compared to each change's at. ISO 8601 UTC. Example: 2026-10-01T00:00:00Z. Omit for 7 days ago.
providerNoOptional lowercase provider id from list_providers, e.g. openai or anthropic. Omit for every provider.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed8 schema fields changed
    • changedInput schema / properties / kind / description
      Previous value: -"Optional change type filter"New value: +"Optional type filter. status = provider state flips; deprecations = deprecation-page line edits; model_retirement = a model id became deprecated or retired; pricing = pricing-page line edits. Omit for all four."
    • addedInput schema / properties / kind / examples
      Added value: +[
+  "model_retirement"
+]
    • changedInput schema / properties / limit / description
      Previous value: -"Max items, default 100, max 500"New value: +"How many changes to return, newest first. Positive integer. Omit for 100."
    • addedInput schema / properties / limit / examples
      Added value: +[
+  100
+]
    • changedInput schema / properties / provider / description
      Previous value: -"Optional provider id, e.g. openai"New value: +"Optional lowercase provider id from list_providers, e.g. openai or anthropic. Omit for every provider."
    • addedInput schema / properties / provider / examples
      Added value: +[
+  "openai",
+  "anthropic"
+]
    • changedInput schema / properties / since / description
      Previous value: -"ISO 8601 timestamp; default 7 days ago. Example: 2026-10-01T00:00:00Z"New value: +"Exclusive lower bound compared to each change's at. ISO 8601 UTC. Example: 2026-10-01T00:00:00Z. Omit for 7 days ago."
    • addedInput schema / properties / since / examples
      Added value: +[
+  "2026-10-01T00:00:00Z"
+]
  2. Added

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), yet the description adds substantial behavior beyond them: freshness SLAs (status rows ~5 min, doc rows every few hours), limit clamping at 500, unknown-provider-returns-empty-not-error, and pricing/quota via x402. That is exactly the extra context annotations cannot express.

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 purpose and routing, and every sentence carries information (types, alternatives, return shape, freshness, clamping, pricing). It is dense and a touch long, packing return fields, quotas, and an alias into one paragraph, but there is little wasted verbiage.

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 no output schema, the description compensates by enumerating the return shape (summary, count, freshness, changes[] with provider, kind, title, detail, source, at), plus ordering, freshness, and edge-case behavior. An agent has everything needed to call and interpret it.

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 coverage is 100%, so baseline is 3; the description still adds value by giving a concrete combined example call and by documenting the limit clamping behavior, which the schema does not. It doesn't go further on `since` semantics beyond what the schema already states.

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+resource ('List the on-demand feed of recent AI and developer API changes') and enumerates the covered event types. It also distinguishes itself from siblings by naming check_api_status and get_digest explicitly, so an agent can select it without opening other schemas.

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?

Gives explicit when-to-use ('a chosen window, one provider, or one kind, when explaining sudden breakage') and when-not ('Not for live up/down ... and not for the once-a-day digest'), naming the alternatives. This is close to ideal routing guidance.

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

All Upstream 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