Skip to main content
Glama

Search Evidence Pack Payment Quote

search_evidence_quote
Read-onlyIdempotent

Returns the payment terms for https://horizonpulse.dev/api/search/evidence (evidence $0.1; USDC on Base only); this tool never runs the check or pays. Pay the 402 over HTTP with x402 v2: GET ?q=x402+payment+protocol (optional n=5-8, default 6). Search evidence pack: one web search, then the top 5-8 result pages are read and returned as short quoted passages (up to 3 per page, 300 characters each) with the source link, title, rank and the time each page was read. Extractive only: no AI-written text, no summaries. Pages that fail are listed with the reason. Not charged when the search has no results or no page can be read. USDC on Base only.

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": "search_evidence_quote"
  }
}

Input Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.2/5.0
Behavior5/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, and the description adds substantive context beyond them: price ($0.1, USDC on Base only), the x402 v2 payment path, the exact deliverable (5-8 pages, up to 3 quotes per page of 300 characters, plus source link, title, rank and read time), the extractive-only constraint, and failure reporting. The free-of-charge conditions are a behavior an agent cannot infer from annotations alone. The mention of 'one web search' describes the underlying API, not this quote call, so it does not conflict with openWorldHint=false.

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 pricing and no-pay constraint are correctly front-loaded, but the text is longer than needed and repeats 'USDC on Base only' verbatim at the start and again at the end. The blockchain sentence could have been stated once, and the endpoint query-string detail is a tangent in a definition for a zero-parameter quote tool.

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 parameterless quote tool with no output schema and full annotation coverage, the description covers price, currency, payment protocol, deliverable shape, billing exceptions and failure handling – nearly everything needed to decide and act. The only shortfall is that it never characterizes the quote response itself (what fields the payment terms come back in), leaving the agent to discover that at call time.

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?

The tool takes zero parameters and the schema is empty, which normally sets a baseline of 4. However, the description surfaces 'GET ?q=x402+payment+protocol (optional n=5-8, default 6)', which are query parameters of the remote endpoint rather than inputs to this tool, and it never says they cannot be supplied here. That is useful context for interpreting the quote but risks an agent trying to pass q or n to a parameterless call.

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 first clause states a specific verb and resource – 'Returns the payment terms for https://horizonpulse.dev/api/search/evidence' – and immediately scopes it with 'this tool never runs the check or pays'. That single sentence separates it from the paid action and from sibling quote tools keyed to other endpoints, and the endpoint URL pins down exactly which resource is being priced.

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?

The description gives a clear operating instruction: the quote is free to call, the actual work must be paid for 'over HTTP with x402 v2', and payment is 'USDC on Base only'. It also states the billing exemption ('not charged when the search has no results or no page can be read'), which is genuine decision-relevant guidance. It does not name a sibling alternative or say explicitly when to prefer this quote over a general search tool, so it stops short of a 5.

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.