Skip to main content
Glama

Tolca: business verification (KYB)

web-search

web_search
Read-onlyIdempotent

Web search with page content: search the web and read the top pages in ONE call. Returns 10 results (title, url, snippet, date) plus the clean text of the best pages (read 1-5), with fetch time, sha256, publication and last-modified dates (each with its source) and canonical URL; a complete flag, and require_complete for all-or-nothing (not charged). French and Canada by default for French queries; official-sources mode (governments, registries, courts, laws); freshness filter; site: restriction. No results = HTTP 404 = not charged. Input: query, optional read, official, lang, country, freshness, site. Costs $0.008 USDC per call (x402 v2, Base or Solana). Send the HTTP header PAYMENT-SIGNATURE with your x402 payment, or call POST https://tolca.tonbot.ca/v1/web-search with an x402 client.

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": {
      "query": "<query>"
    },
    "name": "web_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
langNoSearch language: auto (detected from the query), fr or en
readNoTop pages to fetch and return as clean text (default 3)
siteNoRestrict to one domain
queryYesQuestion or keywords; Brave operators allowed (site:, "exact", -word)
countryNoISO country to prioritize (default CA)
officialNoOnly governments, registries, courts, laws
freshnessNoOnly results from the last 24h, 7d or 30d (default none)
max_charsNoMax characters of text per page (default 6,000; up to 50,000 for whole pages)
require_completeNoIf true, a call that cannot read every available page returns an error and is not charged

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / freshness / description
      Added value: +"Only results from the last 24h, 7d or 30d (default none)"
    • addedInput schema / properties / lang / description
      Added value: +"Search language: auto (detected from the query), fr or en"
  2. Changed2 schema fields changed
    • addedInput schema / properties / max_chars
      Added value: +{
      +  "description": "Max characters of text per page (default 6,000; up to 50,000 for whole pages)",
      +  "maximum": 50000,
      +  "minimum": 1000,
      +  "type": "integer"
      +}
    • addedInput schema / properties / require_complete
      Added value: +{
      +  "description": "If true, a call that cannot read every available page returns an error and is not charged",
      +  "type": "boolean"
      +}
  3. Added

TDQS

A4.1/5.0
Behavior4/5

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

Well beyond the annotations, it discloses the return payload (10 results plus clean text of 1-5 pages, fetch time, sha256, dates with source, canonical URL, complete flag), error semantics (no results = HTTP 404), and that 404s and require_complete failures are not charged. Remaining gap: it never covers batching/concurrency limits or how a failed page read affects partial results outside require_complete.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The purpose is front-loaded, but the rest is a dense semicolon-chained block that mixes the return contract, payment mechanics, defaults, and parameter names into one paragraph. Every clause carries information, yet the scanning cost is high and the payment/endpoint detail could be separated or deferred.

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?

For a paid, open-world search-and-read tool with no output schema, the description covers the return shape, error behavior, billing consequences, default locale behavior, and the auth mechanism (x402 PAYMENT-SIGNATURE header or endpoint). An agent has enough to invoke it correctly and interpret failures.

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 both parameters and enums are already documented; the description mostly restates parameter names. It adds some genuine meaning—require_complete is all-or-nothing and unbilled on failure, read is 1-5—but leaves max_chars, lang semantics, and the exact default values to the schema.

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 opens with a specific verb+resource ("search the web and read the top pages") and states the distinguishing behavior: search plus page-content reading in a single call. An agent can tell this apart from a plain search or a pure extraction tool like extract_url 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 Guidelines4/5

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

It gives concrete conditions: use official-sources mode for governments/registries/courts/laws, freshness for recent-only results, site: to restrict to one domain, and French/Canada defaults for French queries. It does not explicitly say when to prefer this over siblings such as extract_url or summarize, so it stops short of full routing guidance.

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.