Skip to main content
Glama

IKANGAI AI News

What changed since my last check

changes_since
Read-onlyIdempotent

Stories that are new, got a new development, or got a stronger status or a first original source since a time, optionally only for a watchlist of organisations, products, models or packages, and only some kinds of change. Pass the checked_at from the previous reply as since next time, to see each change once. Oldest first; when more is true, call again with that checked_at as since for the rest.

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": {
      "since": "<since>"
    },
    "name": "changes_since"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNo
sinceYesThe checked_at of the previous reply, or an ISO 8601 time such as 2026-11-06T09:00:00Z.
companiesNoOnly stories about any of these organisations, or applying to these products, models or packages, such as OpenAI, gemini-embedding-2 or vllm.
change_typesNoOnly these kinds of change, such as breaking_change and security. Stories not classified yet are included too (change_type null), so a story classified after your check isn't missed.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4/5.0
Behavior4/5

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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed world), and the description adds real behavior beyond them: result ordering (oldest first), a pagination protocol keyed on checked_at/more, and the non-obvious inclusion of unclassified stories so late-classified items are not missed. It references return fields (more, checked_at) without a full return description, but the protocol itself is disclosed.

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?

Two sentences, front-loaded with what the tool returns before the calling protocol, with essentially no filler. The opening enumeration ('new, got a new development, or got a stronger status or a first original source') is dense and slightly hard to parse on first read, but every clause carries information.

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

Completeness4/5

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

With no output schema, the description carries the burden of explaining returns and does so by describing ordering, the more/checked_at pagination loop, and the once-only semantics. Combined with a 75%-documented schema and full annotations, an agent has enough to call this correctly; only the limit parameter and the exact shape of the reply are left unstated.

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 75%, and the description adds meaning to the covered parameters: since is framed as the previous reply's checked_at (enabling once-only delivery), companies as a watchlist of organisations/products/models/packages, and change_types as a filter that still includes as-yet-unclassified stories. The limit parameter is never mentioned, which is the main remaining gap.

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 description states precisely what the tool returns: stories that are new, have a new development, a stronger status, or a first original source since a given time. That is a specific delta/changelog retrieval, clearly distinct in kind from a generic listing. It does not name the siblings (latest_stories, search_stories) to draw the boundary explicitly, which keeps it from a 5.

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?

Strong operational guidance: pass the checked_at from the previous reply as since to see each change only once, and when 'more' is true call again with that checked_at for the remainder. What is missing is explicit routing versus the sibling tools (e.g. when to prefer latest_stories or search_stories), so no alternatives or exclusions are named.

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