Skip to main content
Glama

Data Delaware

by io.github.pipeworx-io

Ask Pipeworx — Grounded

ask_pipeworx_grounded
Read-onlyIdempotent

Hallucination-resistant answer mode for high-stakes reads. Same routing as ask_pipeworx — picks the right tool from 5,724 across 1497 sources, fills arguments, fetches the data — then EXTRACTS the answer using ONLY what the tool result contains. Returns {answer, evidence (verbatim quote), confidence, source, fetched_at, refusal_reason:null} on success, OR an explicit refusal {answer:null, refusal_reason:"not_in_source"|"no_tool_match"|"tool_error"|"data_truncated"|"llm_error"} when the data doesn't directly answer. Use whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts (financial verdicts, legal claims, medical lookups, public statements). Costs one extra LLM call vs ask_pipeworx — prefer ask_pipeworx for casual lookups.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
qNoAlias for question.
textNoAlias for question.
inputNoAlias for question.
queryNoAlias for question.
promptNoAlias for question.
questionYesYour question in natural language. Accepts query, q, prompt, text, input as aliases.

TDQS

A4.7/5.0
Behavior5/5

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

Annotations already declare readOnlyHint and idempotentHint, so the description's added detail on return format (success and refusal objects with specific fields like refusal_reason) and refusal reason categories goes beyond structural hints. It also discloses that it runs an extra LLM call, which is a non-obvious behavioral trait not captured in 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 information-dense with no filler. It front-loads the core purpose ('Hallucination-resistant answer mode') and then efficiently covers routing, extraction, return contract, refusal cases, usage conditions, and cost. Every sentence earns its place.

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 tool with no output schema, the description fully compensates by detailing the exact success and refusal return formats. It also covers when to use it (high-stakes reads) and when not (casual), plus cost implications. An agent has all necessary information to invoke and interpret the tool correctly.

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 description coverage is 100%: the single required parameter 'question' is described in the schema, including aliases. The description does not add new parameter meaning—it only notes the question is in natural language and that routing is shared with ask_pipeworx. Baseline 3 is appropriate since the schema carries the semantic load.

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 opens with 'Hallucination-resistant answer mode for high-stakes reads,' which clearly states a specific purpose and distinguishes it from the sibling ask_pipeworx. It further clarifies the mechanism (extracting answers only from tool results) and explicitly names the sibling it is not.

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 'Use whenever' conditions (when answers will be quoted, cited, acted on) and contrasts with casual lookups, stating 'prefer ask_pipeworx for casual lookups.' It also mentions an extra LLM call cost as a trade-off, making the choice criteria concrete.

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

All Data Delaware 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

Many tools have overlapping purposes, e.g., ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, deep_research, and validate_claim all route queries to the same data sources with only subtle differences. Similarly, bet_research, polymarket_edges, polymarket_arbitrage, and polymarket_edge_tracker all analyze prediction markets, making it hard for an agent to pick the right one without deep reading of descriptions.

Naming Consistency3/5

Tool names follow a mix of patterns: some are verb_noun (generate_llms_txt, list_subscriptions), some noun_verb (ai_visibility_check, bet_research), and some are just nouns (datasets, metadata). The ask_pipeworx family has consistent prefixes but suffixes vary. Overall readable but inconsistent.

Tool Count2/5

34 tools is excessive for a coherent server. The server tries to be a Swiss Army knife covering data lookup, prediction markets, Delaware open data, memory, subscriptions, and misc tools like generate_llms_txt and scan_dependency. Many tools feel tacked on, and the count makes it unwieldy for an agent to navigate.

Completeness3/5

The server covers multiple domains thoroughly (data query via Pipeworx variants, prediction markets with arbitrage and edges, Delaware open data, memory, subscriptions). However, there are gaps: no tool for managing custom pipelines or for updating data. For the broad scope, it is decent but not fully comprehensive.

Resources