Skip to main content
Glama
Sign In

Hyperresearch Answers

by ai.hyperresearch
OverviewDiscussionsAdmin

Search the web and structured sources

search

Finds the best sources on a topic across the live web plus 90+ structured public data sources, including SEC EDGAR company filings, FDIC bank data, FEC campaign-finance and lobbying disclosures, USPTO patents and trademarks, FRED and Census economic series, ClinicalTrials.gov and openFDA, NOAA weather and climate records, scholarly databases and books, market data and posts on X, with the exact passages. Use it when you need several sources to compare or build a table from (competitor lists, pricing tables, market reports), or when ask found nothing. Pass the user's overall goal as objective. Prices: standard 5¢ per call (the default), max 15¢ for hard lookups. A paywalled article the call reads may add a surcharge of 1.5 times the article's licence cost (licence price plus transaction fee), rounded up to the cent. Each call is charged to the user's prepaid Hyperresearch Answers balance.

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": "search"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNostandard (5¢, the default) or max (15¢: every provider, plus structured data rows and PDF tables, for hard lookups).standard
queryYesWhat to find, as a question or a precise phrase.
objectiveNoOptional: your overall task in a sentence or two (what this query is a step toward). Used where adaptive search is enabled to pick follow-up queries, ignored otherwise; never sent to a search index as typed.
max_resultsNoHow many ranked sources to return (1-100, default 10). Up to 25 at the mode price; past 25, +5¢ plus 2¢ per started 10 results.
exclude_textNoShort phrases that must not appear in the returned text.
include_textNoShort phrases that must all appear in the returned text.
exclude_domainsNoNever sources on these domains (or subdomains).
include_domainsNoOnly sources on these domains (and subdomains), e.g. ["sec.gov"].
max_chars_totalNoMost characters of passage text in the whole response.
end_published_dateNoOnly sources published on or before this ISO date (YYYY-MM-DD). Undated sources are left out when a date is set.
max_chars_per_resultNoMost characters of passage text per result.
start_published_dateNoOnly sources published on or after this ISO date (YYYY-MM-DD). Undated sources are left out when a date is set.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed10 schema fields changed
    • addedInput schema / properties / end_published_date
      Added value: +{
+  "description": "Only sources published on or before this ISO date (YYYY-MM-DD). Undated sources are left out when a date is set.",
+  "maxLength": 40,
+  "type": "string"
+}
    • addedInput schema / properties / exclude_domains
      Added value: +{
+  "description": "Never sources on these domains (or subdomains).",
+  "items": {
+    "maxLength": 253,
+    "type": "string"
+  },
+  "maxItems": 50,
+  "type": "array"
+}
    • addedInput schema / properties / exclude_text
      Added value: +{
+  "description": "Short phrases that must not appear in the returned text.",
+  "items": {
+    "maxLength": 100,
+    "type": "string"
+  },
+  "maxItems": 5,
+  "type": "array"
+}
    • addedInput schema / properties / include_domains
      Added value: +{
+  "description": "Only sources on these domains (and subdomains), e.g. [\"sec.gov\"].",
+  "items": {
+    "maxLength": 253,
+    "type": "string"
+  },
+  "maxItems": 50,
+  "type": "array"
+}
    • addedInput schema / properties / include_text
      Added value: +{
+  "description": "Short phrases that must all appear in the returned text.",
+  "items": {
+    "maxLength": 100,
+    "type": "string"
+  },
+  "maxItems": 5,
+  "type": "array"
+}
    • addedInput schema / properties / max_chars_per_result
      Added value: +{
+  "description": "Most characters of passage text per result.",
+  "maximum": 100000,
+  "minimum": 1,
+  "type": "integer"
+}
    • addedInput schema / properties / max_chars_total
      Added value: +{
+  "description": "Most characters of passage text in the whole response.",
+  "maximum": 1000000,
+  "minimum": 1,
+  "type": "integer"
+}
    • changedInput schema / properties / max_results / description
      Previous value: -"How many ranked sources to return (1-25, default 10). The price does not change."New value: +"How many ranked sources to return (1-100, default 10). Up to 25 at the mode price; past 25, +5¢ plus 2¢ per started 10 results."
    • changedInput schema / properties / max_results / maximum
      Previous value: -25New value: +100
    • addedInput schema / properties / start_published_date
      Added value: +{
+  "description": "Only sources published on or after this ISO date (YYYY-MM-DD). Undated sources are left out when a date is set.",
+  "maxLength": 40,
+  "type": "string"
+}
  2. Changed1 schema field changed
    • addedInput schema / properties / objective
      Added value: +{
+  "description": "Optional: your overall task in a sentence or two (what this query is a step toward). Used where adaptive search is enabled to pick follow-up queries, ignored otherwise; never sent to a search index as typed.",
+  "maxLength": 2000,
+  "type": "string"
+}
  3. First observed

TDQS

A3.8/5.0
Behavior3/5

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

The description adds real behavior beyond the annotations: per-call cost, max-mode cost, paywall surcharge math, and that charges hit a prepaid balance — which incidentally explains the readOnlyHint=false on an otherwise read-like tool. However, it does not disclose result shape, whether passages are truncated, or how the include/exclude filters interact with ranking, so the disclosure is cost-heavy but retrieval-light.

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 and the 90+ source list are front-loaded well, but the three trailing sentences on pricing restate the mode enum and the max_results surcharge rule almost verbatim from the schema. The dense source enumeration is justified; the duplicated tariff prose is not.

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 12-parameter tool with no output schema, the description covers what to pass (query, objective), which mode to pick, and what a call costs, which is enough to invoke it correctly. The remaining gap is the response shape — only 'with the exact passages' hints at it, and nothing says how ranked sources versus structured data rows are returned.

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 every parameter already documents itself, and this sets the baseline at 3. The description contributes only a repetition of the 5¢/15¢ mode pricing (also in the mode enum and max_results description) and one useful steer, 'Pass the user's overall goal as objective', which the schema already qualifies.

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 an unusually concrete resource: finding ranked sources across the live web plus 90+ named structured sources (SEC EDGAR, FDIC, FEC, USPTO, FRED, ClinicalTrials.gov, openFDA, NOAA). The enumeration makes it immediately distinguishable from the ask/get_answer siblings, which are single-answer tools.

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 triggering conditions ('need several sources to compare or build a table from') with concrete examples, plus a fallback rule ('when ask found nothing') that routes the agent from the sibling. It stops short of explicit exclusions such as when a single factual answer should go to ask instead, so the reverse routing is only implied.

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

All Hyperresearch Answers 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