Skip to main content
Glama
Sign In

Crawlbase

by io.github.pipeworx-io
OverviewDiscussionsAdmin

Deep Research

deep_research
Read-onlyIdempotent

ACCOUNT REQUIRED (free — sign in via GitHub at https://pipeworx.io/signup; depth:"thorough" needs a paid plan). If you are not signed in, use ask_pipeworx instead — it works on every tier. Grounded multi-source research across Pipeworx's 1911 STRUCTURED data sources (SEC filings, FRED/BLS economics, FDA, USPTO patents, markets, science, government records, etc.) in ONE call — this is NOT open-web search. Decomposes your question into focused facets, routes each to the right one of 7,321 tools IN PARALLEL, and returns a findings packet: verbatim evidence + confidence + source + fetched_at + a stable pipeworx:// citation per finding, with explicit gaps[] for facets the data couldn't answer (never invented). Best for broad/multi-part questions over structured data ("compare X and Y's regulatory + financial exposure", "research the filings + market picture for ACME"). For a single lookup use ask_pipeworx (one LLM call, not many). For BREAKING or colloquial CURRENT-NEWS / "what's the world saying about X" topics, prefer ask_pipeworx — it routes to live news APIs and the *-news-feeds packs; deep_research returns mostly empty gaps[] when the topic isn't in the structured catalog. Second-hop iteration: depth:"standard" re-angles unanswered gaps (gap recovery); depth:"thorough" additionally chases the best leads from the first pass — so multi-step questions resolve in one call. Every finding carries a hop field and a citation_uri — a resolvable pipeworx:// record URI, present only when the source emits one that resources/read can actually serve, so a citation you get back is always fetchable. "standard" and "thorough" also return contradictions[] flagging findings that disagree. Large records are semantically excerpted to the passages relevant to each facet (not head-truncated), so answers deep in a long filing/series aren't missed. Expect 15-60s (thorough with its follow-up + contradiction pass: up to ~90s).

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "depth": "quick",
      "question": "What is the current US unemployment rate and how has it changed over the past year?"
    },
    "name": "deep_research"
  }
}

Input Schema

NameRequiredDescriptionDefault
qNoAlias for question.
askNoAlias for question.
textNoAlias for question.
depthNoHow many facets to research in parallel: quick=3 (single hop), standard=3 (default; adds a gap-recovery hop that re-angles unanswered facets + a contradictions[] scan across findings), thorough=6 (paid; adds a full iterative hop that chases leads + recovers gaps, plus the contradictions[] scan).
inputNoAlias for question.
queryNoAlias for question.
promptNoAlias for question.
messageNoAlias for question.
questionYesThe research question, in natural language. Broad/multi-part is fine — decomposition is the point. Accepts query, q, prompt, text, input, ask, message as aliases.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed9 schema fields changed
    • addedInput schema / examples
      Added value: +[
+  {
+    "depth": "quick",
+    "question": "What is the current US unemployment rate and how has it changed over the past year?"
+  }
+]
    • addedInput schema / properties / ask
      Added value: +{
+  "description": "Alias for question.",
+  "type": "string"
+}
    • addedInput schema / properties / input
      Added value: +{
+  "description": "Alias for question.",
+  "type": "string"
+}
    • addedInput schema / properties / message
      Added value: +{
+  "description": "Alias for question.",
+  "type": "string"
+}
    • addedInput schema / properties / prompt
      Added value: +{
+  "description": "Alias for question.",
+  "type": "string"
+}
    • addedInput schema / properties / q
      Added value: +{
+  "description": "Alias for question.",
+  "type": "string"
+}
    • addedInput schema / properties / query
      Added value: +{
+  "description": "Alias for question.",
+  "type": "string"
+}
    • changedInput schema / properties / question / description
      Previous value: -"The research question, in natural language. Broad/multi-part is fine — decomposition is the point."New value: +"The research question, in natural language. Broad/multi-part is fine — decomposition is the point. Accepts query, q, prompt, text, input, ask, message as aliases."
    • addedInput schema / properties / text
      Added value: +{
+  "description": "Alias for question.",
+  "type": "string"
+}
  2. Changed1 schema field changed
    • changedInput schema / properties / depth / description
      Previous value: -"How many facets to research in parallel: quick=3 (single hop), standard=5 (default; adds a gap-recovery hop that re-angles unanswered facets + a contradictions[] scan across findings), thorough=8 (paid; adds a full iterative hop that chases leads + recovers gaps, plus the contradictions[] scan)."New value: +"How many facets to research in parallel: quick=3 (single hop), standard=3 (default; adds a gap-recovery hop that re-angles unanswered facets + a contradictions[] scan across findings), thorough=6 (paid; adds a full iterative hop that chases leads + recovers gaps, plus the contradictions[] scan)."
  3. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Goes well beyond the annotations: discloses an account requirement (paid for thorough), latency expectations (15-60s, ~90s for thorough), the shape of the return packet (evidence + confidence + source + fetched_at + citation, gaps[], contradictions[], hop field), and the guarantee that citations are resolvable only when the source emits one. The annotations already cover the safety profile, so the remaining gap is minor — it does not say what happens on quota exhaustion or partial failures mid-run.

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?

Strongly front-loaded with the auth constraint and the alternative routing, which is the right order. But it is a single dense block with real redundancy: ask_pipeworx routing is argued three times, the citation_uri/resolvability point twice, and contradictions[] twice — several sentences could be merged without losing information.

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 high-complexity, long-running, multi-source research tool with no output schema, the description supplies everything an agent needs to call it correctly and interpret results: cost/auth gating, latency budget, output packet fields, gap/contradiction semantics, and citation fetchability.

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% and the schema already documents depth's three values, hop counts, the gap-recovery hop, and the alias set, so the baseline applies. The description's second-hop paragraph largely restates the depth enum; its only genuine addition is that thorough requires a paid plan, which it already covers under account requirements.

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 with explicit scope: multi-source grounded research over 1,911 structured data sources, and explicitly negates the nearest misreading ("this is NOT open-web search"). It also names the sibling it is not (ask_pipeworx) and the question shapes it targets, so an agent can pick it 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?

Gives explicit when-to-use (broad/multi-part questions over structured data, with two concrete example phrasings), when-not (single lookup → ask_pipeworx; breaking/colloquial current news → ask_pipeworx with the reason: empty gaps[]), and a depth-selection rule (standard vs thorough). Nothing about routing 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 Crawlbase 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