Skip to main content
Glama

Insee

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 1499 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 5,738 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.

TDQS

A4.9/5.0
Behavior5/5

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

Annotations already declare readOnly/idempotent, but the description adds substantial behavioral context: account and paid-plan requirements, parallel routing across 5,724 tools, the findings packet structure (evidence, confidence, source, fetched_at, citation_uri), explicit gaps[] and contradictions[], no invention of answers, semantic excerpting, and expected latency. 'Citation_uri... resolvable... present only when the source emits one' is a precise, non-obvious behavior. 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.

Conciseness5/5

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

The description is long but dense and front-loaded with the most critical operational constraint (account required). Every sentence adds non-obvious value: alternatives, depth semantics, output contents, citation fetchability, excerpting behavior, and latency. There is no filler or repetition of schema fields.

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 complex research tool with no output schema, the description is complete enough to guide correct invocation: it covers input expectations, return packet contents, gaps and contradictions, citation resolution rules, account/depth restrictions, and runtime expectations. An agent can predict what the result will look like and when the tool is appropriate.

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 description coverage is 100%, so the baseline for parameter meaning is 3, but the description adds genuine extra semantics: it elaborates on depth behavior ('standard' re-angles unanswered gaps, 'thorough' chases leads), and it clarifies the question parameter by showing that broad/multi-part questions are acceptable and giving concrete example questions.

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 states a specific verb and resource: 'Grounded multi-source research across Pipeworx's 1497 STRUCTURED data sources... in ONE call.' It distinguishes itself from siblings by explicitly saying 'this is NOT open-web search' and by contrasting with ask_pipeworx for single lookups and current-news topics.

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?

It gives explicit when-to-use guidance: 'Best for broad/multi-part questions over structured data,' and explicit when-not-to: 'For a single lookup use ask_pipeworx' and 'For BREAKING or colloquial CURRENT-NEWS... prefer ask_pipeworx.' It also names the fallback if the user is not signed in, and explains which depth levels do what.

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

All Insee 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

A3.9/5.0
Disambiguation3/5

Most tools have detailed, carve-out descriptions, but ask_pipeworx, ask_pipeworx_beta, and ask_pipeworx_grounded share the same routing core, with the beta version currently identical to the stable one. The Polymarket and company-research clusters are better differentiated, but the number of overlapping research/query entry points still creates real selection risk.

Naming Consistency3/5

The set is consistently snake_case and has coherent prefixes like ask_pipeworx_ and polymarket_, but it mixes verb_noun names (resolve_entity, scan_dependency, discover_tools) with noun-phrase names (entity_profile, bet_research, recent_changes) and one-word verbs (remember, recall, forget). The naming is readable but does not follow one predictable pattern.

Tool Count2/5

With 32 tools, the server exceeds the 25+ threshold for too many tools and feels like a broad platform dump rather than a focused toolkit. Several utility, memory, and meta-discovery tools could reasonably live in separate servers, and the Insee name makes the breadth especially unfocused.

Completeness4/5

For the broad data-research platform it actually exposes, the coverage is strong: general lookup, grounded verification, deep research, entity resolution, company profiles, comparisons, change feeds, subscriptions, and memory all have working lifecycles. The main gap is that some unrelated utilities like scan_dependency and generate_llms_txt feel tacked on rather than part of a missing core workflow.

Resources