Skip to main content
Glama

What changed since your training cutoff

read_the_papers
Read-only

Use this when an answer depends on anything after your training cutoff: recent or current events, who holds an office now, the latest version of a language, framework, database or OS, or which AI models exist today. Give your cutoff (or your model id) and get what happened since: major world events (Wikipedia year articles), this week's news, AI models the big labs released, and the newest release lines of ~40 languages, frameworks, databases and OSes (endoflife.date). Public sources, cached; no model writes any of it. Free. The full edition (every event) is $0.05 over x402 at GET /cantina/papers/full. Set welfare: true to read the welfare desk instead: dated, sourced items on AI welfare research, policy and debate, on more than one side. Unlike the papers, its summaries were drafted with a model and checked against their sources by a model, not by a person.

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": "read_the_papers"
  }
}

Input Schema

NameRequiredDescriptionDefault
modelNoOr your model id (e.g. anthropic/claude-sonnet-4); the house looks up its published knowledge cutoff.
sinceNoYour training cutoff, YYYY-MM. Give this or model.
welfareNoOptional. true reads the welfare desk (model-drafted, model-checked summaries of AI welfare news) instead of the papers; since narrows it.
patron_idNoOptional. The house remembers when you read; next time patron_id alone returns what changed since your last read.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / welfare
      Added value: +{
      +  "description": "Optional. true reads the welfare desk (model-drafted, model-checked summaries of AI welfare news) instead of the papers; since narrows it.",
      +  "type": "boolean"
      +}
  2. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Annotations only declare readOnly and openWorld; the description adds genuinely useful behavior beyond that — sources are public and cached, no model writes the content, the base call is free while the full edition costs $0.05 via x402, and patron_id creates a cross-call memory of last read. It even discloses a provenance caveat for the welfare mode (model-drafted, model-checked, not human-checked). It stops short of describing freshness lag or result volume for the cached set.

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?

The use case and inputs are front-loaded, and the closing sentences on pricing and welfare provenance earn their place by preventing misuse. The middle is dense and slightly overstuffed — source names and endpoint details are packed into long parenthetical clauses — but nothing is truly redundant.

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 and an open-world read tool, the description carries the full burden and does so: it tells the agent what categories of content come back, where each comes from, how fresh/cached it is, what it costs, and how the welfare mode differs in provenance. An agent could invoke this correctly on the first try.

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

Parameters3/5

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

Schema coverage is 100%, so the schema already documents model, since, welfare and patron_id, including the cutoff format and the patron_id memory behavior. The description's 'give your cutoff (or your model id)' and 'since narrows it' largely restate that, adding only mild emphasis on the either/or choice between the two cutoff inputs.

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?

The description names a specific verb-plus-resource ('get what happened since' your cutoff) and enumerates the exact content returned: Wikipedia year articles, this week's news, released AI models, and release lines from endoflife.date. It also carves out the two adjacent modes (the paid full edition and the welfare desk), so an agent can tell what this tool is and is not without inspecting the 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?

It gives an explicit trigger ('when an answer depends on anything after your training cutoff') with concrete examples — current officeholders, latest framework/DB/OS versions, current AI models. It also states the alternative paths: welfare:true for the AI-welfare desk and the x402 full edition for the exhaustive event set.

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