Agent Tools

web_screenshot

Screenshot any public web page with a real headless Chrome: url in, PNG or JPEG out as base64 in JSON, plus final URL after redirects, HTTP status, page title and size. Set viewport width and height, or full_page=true for the whole page. For agents that need to see a page, check a layout or keep visual proof. Price $0.015 USDC per call via x402. Example output: {"url":"https://example.com/","final_url":"https://example.com/","http_status":200,"title":"Example Domain","width":1280,"height":800,"full_page":false,"format":"png","bytes":21034,"image_base64":"iVBORw0KGgo...","data_url_prefix":"data:image/png;base64,"}

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": {
      "url": "<url>"
    },
    "name": "web_screenshot"
  }
}

Input Schema

Name	Required	Description
`url`	Yes	Public http(s) URL
`width`	No	320 to 1920, default 1280
`format`	No
`height`	No	240 to 1600, default 800
`full_page`	No	true for full page

Schema Changelog

Changes observed during successful MCP inspections.

AddedOct 30, 2026

TDQS

A4.1/5.0

Behavior4/5

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

With no annotations, the description carries the load well: it discloses the engine (headless Chrome), post-redirect URL, HTTP status, output format, and notably the cost model ($0.015 USDC per call via x402) — critical for a paid endpoint. It omits failure modes, timeouts, and what happens on unreachable pages.

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 the core capability and parameters, with pricing and example moved to the end. The embedded example output is long but justified since there is no output schema; every remaining sentence provides distinct 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?

For a 5-param tool with no annotations and no output schema, the description supplies the missing return-value detail via a full example JSON and adds the payment/auth-relevant x402 note. Error behavior and timeout handling remain unstated, keeping it short of a 5.

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 80%, so the schema already documents url, width, height and full_page ranges and defaults. The description restates viewport sizing and full_page but adds little syntax beyond the schema; format's enum is explained only implicitly ('PNG or JPEG out'). Baseline 3 applies.

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 ('Screenshot any public web page with a real headless Chrome') and enumerates the concrete outputs (PNG/JPEG base64, final URL, HTTP status, title, size). This clearly separates it from text-oriented siblings like web_read_full, web_to_markdown and url_metadata.

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?

Gives clear usage context: 'For agents that need to see a page, check a layout or keep visual proof.' That frames when to reach for it, but it never names the alternative tools (web_read_full, web_to_markdown) or states when not to use it.

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

All Agent Tools 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?