Skip to main content
Glama

Hex Pm

by io.github.pipeworx-io

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 1517 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 5,798 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).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
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).
questionYesThe research question, in natural language. Broad/multi-part is fine — decomposition is the point.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. 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)."
  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), thorough=8 (paid; adds a full iterative hop that chases leads + recovers gaps, plus a contradictions[] scan across findings)."New 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)."
  3. Changed1 schema field changed
    • changedInput schema / properties / depth / description
      Previous value: -"How many facets to research in parallel: quick=3, standard=5 (default), thorough=8 (paid plans). \"thorough\" also runs a second ITERATIVE hop — a planner inspects the first-pass findings/gaps and chases the most valuable leads or recovers gaps, resolving multi-step questions in one call."New 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), thorough=8 (paid; adds a full iterative hop that chases leads + recovers gaps, plus a contradictions[] scan across findings)."
  4. Changed1 schema field changed
    • changedInput schema / properties / depth / description
      Previous value: -"How many facets to research in parallel: quick=3, standard=5 (default), thorough=8 (paid plans)."New value: +"How many facets to research in parallel: quick=3, standard=5 (default), thorough=8 (paid plans). \"thorough\" also runs a second ITERATIVE hop — a planner inspects the first-pass findings/gaps and chases the most valuable leads or recovers gaps, resolving multi-step questions in one call."
  5. Added

TDQS

A4.5/5.0
Behavior5/5

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

Annotations already mark this readOnly/openWorld/idempotent/non-destructive, and the description adds substantial context beyond them: account/auth tier requirements, honest-gap behavior ('explicit gaps[]... never invented'), the contradictions[] scan in standard/thorough, semantic excerpting of large records rather than head-truncation, and latency expectations (15-60s, thorough up to ~90s). No contradiction with annotations.

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

Conciseness2/5

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

The coherent content is well front-loaded (auth, scope, output packet, routing guidance), but the middle of the description is corrupted with repeated 'For a single lookup use ask_pipeworx instead.' phrases and garbled token fragments, which adds noise, wastes tokens, and obscures the citation_uri disclosure that leads into 'so a citation you get back is always fetchable.' This is a serious structural defect.

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 complex parallel-research tool, the surviving coherent text covers nearly everything an agent needs: auth tiers, alternative routing, data source scope, the findings-packet return shape, honesty guarantees, contradiction handling, excerpting behavior, and latency. The only loss is the partially garbled citation_uri explanation, which keeps it from a 5.

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% and the schema already richly documents both parameters, including the quick/standard/thorough facet counts and the paid gating of thorough. The description adds value on top with operational context: the paid-plan requirement, expected latency per depth, and the account prerequisite. Marginal gains over the schema, but real ones.

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 opening sentences nail the purpose with a specific verb, resource, and mechanism: 'Grounded multi-source research across Pipeworx's 1517 STRUCTURED data sources... in ONE call — this is NOT open-web search' plus 'Decomposes your question into focused facets, routes each to the right one of 5,798 tools IN PARALLEL.' It also distinguishes itself from its sibling by naming what it is not (open-web search) and pointing to ask_pipeworx for single lookups.

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?

Provides explicit when-to-use guidance with conditions and named alternatives: 'If you are not signed in, use ask_pipeworx instead — it works on every tier,' 'Best for broad/multi-part questions over structured data,' and 'For a single lookup use ask_pipeworx instead.' This is exactly the routing clarity an agent needs.

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

All Hex Pm toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.8/5.0
Disambiguation2/5

Several tools occupy overlapping question-answering territory: ask_pipeworx_beta currently behaves identically to ask_pipeworx, while ask_pipeworx_grounded, deep_research, and validate_claim all route the same data catalog and differ mainly in output guarantees. The six Polymarket tools also split edge detection, arbitrage, and fill-risk in ways that are easy for an agent to conflate. Clear exceptions like the memory and subscription trios keep it from a 1.

Naming Consistency4/5

Names are uniformly lowercase snake_case and most follow a readable verb-first or domain-prefixed pattern (get_package, list_releases, scan_dependency, ask_pipeworx_*). The Polymarket family uses noun phrases after a prefix (polymarket_edges, polymarket_fill_risk) and a few names are noun-first (entity_profile, recent_changes), which is a minor inconsistency rather than chaos.

Tool Count2/5

35 tools is well beyond the comfortable 3-15 range and even above the 16-25 heavy range. The broad Pipeworx data scope justifies some expansion, but identical ask_pipeworx_beta, six overlapping Polymarket tools, and unrelated utility families (Hex.pm, AI visibility, memory, llms.txt) suggest bloat rather than deliberate scoping.

Completeness4/5

Within its main data-access purpose, the surface is unusually complete: query (ask_pipeworx), grounded verification (ask_pipeworx_grounded/validate_claim), deep research, entity resolution/profiling, comparison, change feeds, and search-within are all present, and memory/subscription subdomains have full CRUD. There are minor gaps for the package side (no docs/dependents) and the hodgepodge of domains makes a single 'complete' surface hard to define, but no workflow hits a hard dead end.

Resources