Skip to main content
Glama

Tollkit

by io.github.UltraStarz
OverviewDiscussionsAdmin

Web search

web_search
Read-only

Search the web and get Google's top results as clean JSON: title, URL, snippet and date for each, plus the direct answer when Google shows one. Optional filters: freshness (past hour, day, week, month or year), include_domains or exclude_domains (up to 5 sites each), and type "news" for news articles with publisher and date. Up to 10 results. To get the pages' full text in the same call, use search_and_read.

$0.003 USDC per call over x402. Failed calls cost nothing. Call without payment to get a quote.

When to use: You need sources or facts and don't have URLs yet; the snippets often answer it on their own. Use instead: search_and_read when you also need the full text of the top pages in the same call; crypto_news for crypto coverage with a mood read. Parameters: query is required. num: 1-10 results, default 5. country: two-letter code for local results. freshness, include_domains and exclude_domains narrow the results and can combine; very narrow filters can return nothing (refused free). type "news" searches news articles only. Returns: results[] with position, title, url, snippet and date (publisher for news), the answer box when Google shows one, and the filters applied.

Input Schema

NameRequiredDescriptionDefault
numNoHow many results, 1-10 (default 5).
typeNo"news" searches news articles instead of the whole web.
queryYesWhat to search for.
countryNoTwo-letter country code, e.g. "us".
paymentNoBase64 x402 payment payload. Omit it to receive a quote; sign that and call again.
freshnessNoOnly results from the past hour, day, week, month or year.
exclude_domainsNoNever results from these sites.
include_domainsNoOnly results from these sites, e.g. ["reuters.com"].

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / num / description
      Added value: +"How many results, 1-10 (default 5)."
  2. Changed4 schema fields changed
    • addedInput schema / properties / exclude_domains
      Added value: +{
+  "description": "Never results from these sites.",
+  "items": {
+    "type": "string"
+  },
+  "maxItems": 5,
+  "type": "array"
+}
    • addedInput schema / properties / freshness
      Added value: +{
+  "description": "Only results from the past hour, day, week, month or year.",
+  "enum": [
+    "hour",
+    "day",
+    "week",
+    "month",
+    "year"
+  ],
+  "type": "string"
+}
    • addedInput schema / properties / include_domains
      Added value: +{
+  "description": "Only results from these sites, e.g. [\"reuters.com\"].",
+  "items": {
+    "type": "string"
+  },
+  "maxItems": 5,
+  "type": "array"
+}
    • addedInput schema / properties / type
      Added value: +{
+  "description": "\"news\" searches news articles instead of the whole web.",
+  "enum": [
+    "web",
+    "news"
+  ],
+  "type": "string"
+}
  3. Added

TDQS

A4.8/5.0
Behavior5/5

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

Annotations cover only readOnly/openWorld, but the description adds substantial context beyond them: exact pricing ($0.003 USDC over x402), that failed calls are free, the quote-then-pay flow via the payment param, and the refusal behavior ('very narrow filters can return nothing (refused free)'). This is exactly the behavioral detail an agent needs before spending money.

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 output shape, then filters, pricing, and when-to-use routing. Well-organized with clear sectioning, though it runs long and restates some schema-provided details (num range, freshness enum) that could be trimmed.

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?

No output schema exists, yet the description fully enumerates the return shape (results[] with position/title/url/snippet/date, answer box, applied filters), and all 8 params plus the payment flow are covered. An agent has everything needed to call it correctly.

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 the baseline is 3, but the description adds genuine meaning: that freshness/include_domains/exclude_domains 'can combine' and that very narrow combinations can return empty results. The payment/quote flow and the num default are also restated usefully.

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 ('Search the web and get Google's top results as clean JSON') and immediately distinguishes itself from siblings by naming search_and_read for full text and crypto_news for crypto coverage. An agent can pick this over its neighbors without opening either 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?

Explicit 'When to use' ('You need sources or facts and don't have URLs yet') and 'Use instead' sections routing to search_and_read and crypto_news with the exact condition that selects each. Nothing is left to inference.

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

All Tollkit 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