Microsoft Research Blog — AI Research Announcements (msrwatch)

data_preview

Read-onlyIdempotent

✅ No API key needed. Listing: msrwatch: Microsoft Research Blog — AI Research Announcements. Price 0.01 USDC/query (max 20 queries/session). Sample questions: What has Microsoft Research published lately?; New AI research blog posts from Microsoft. FREE preview — no key, no payment. Try one of the sample questions now.

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": "data_preview"
  }
}

Input Schema

Name	Required	Description	Default
`slug`	No	Public listing slug. Defaults to the routed session's listing when connected via /mcp/data/{slug}/http.
`question`	No	Optional free-text question you'd ask this data (echoed back).

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 9, 2026

TDQS

C2.9/5.0

Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive, so safety is covered. The description does add useful context beyond them: no API key required, and a session cap of max 20 queries. However, the pricing line ('Price 0.01 USDC/query') sits adjacent to 'FREE preview — no key, no payment' and reads as self-contradictory, muddying rather than clarifying cost behavior.

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?

Short overall and front-loads the strongest fact ('No API key needed'), but it wastes space on an emoji, a marketing name, and promotional sample questions that do not help an agent invoke the tool correctly.

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

Completeness3/5

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

For a simple, zero-required-parameter read tool with no output schema and full schema coverage, the description is roughly adequate. The murky price/‘FREE’ messaging and the absence of any statement about what the preview actually returns leave a gap an agent must resolve by trial.

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 both the slug and question parameters, including the slug defaulting to the routed session's listing. The description adds nothing about either parameter; the sample questions only illustrate the kind of question accepted, not its semantics. Baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description identifies the resource (msrwatch: Microsoft Research Blog) and calls it a 'FREE preview', but it never states a clean verb+resource purpose. Marketing framing ('Try one of the sample questions now') and pricing details crowd out a direct statement of what the tool returns.

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

Usage Guidelines2/5

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

No explicit when-to-use versus alternatives is given. The paid price (0.01 USDC/query) implies data_session_query is the full version and this is a taste, but the description never names or contrasts the sibling, and gives no exclusions or prerequisites beyond 'no key needed'.

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

All Microsoft Research Blog — AI Research Announcements (msrwatch) tools Inspect

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

Need Help?