Skip to main content
Glama

Foodish

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 5,743 across 1500 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?

The description reveals behavior beyond the readOnly/openWorld/idempotent annotations: it extracts answers using only the tool result, returns a structured evidence object, may explicitly refuse with enumerated reasons, and costs an extra LLM call. No contradiction with annotations exists.

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 front-loaded with the core distinction, then efficiently moves through behavior, output shape, use cases, and cost/alternative guidance. Every sentence carries decision-relevant information without redundancy.

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?

Given there is no output schema, the description compensates by specifying the success shape and all refusal categories. It also covers cost, routing behavior, and when to choose the sibling, making it complete for safe invocation.

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 fully documents the question parameter and its aliases. The description does not add parameter-level detail, so the baseline score of 3 is appropriate.

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 names a specific capability — a grounded, hallucination-resistant answer mode — and clearly distinguishes it from the ungrounded ask_pipeworx sibling by emphasizing extraction solely from tool results. The verb 'answers' and the explicit result/refusal contract make the tool's purpose unmistakable.

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 for high-stakes, quotable, or actionable answers, and explicitly says to prefer the cheaper ask_pipeworx for casual lookups. This directly informs tool selection among siblings.

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

All Foodish 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
Disambiguation5/5

Every tool has a clearly distinct purpose, with detailed descriptions that differentiate between similar-sounding tools like ask_pipeworx, ask_pipeworx_grounded, and deep_research. The Polymarket-related tools each focus on a specific aspect (arbitrage, edges, tracking, fill risk, cross-venue spread), and memory/subscription tools are neatly separated.

Naming Consistency4/5

Most tool names follow a verb_noun or noun_verb pattern with underscores (e.g., ask_pipeworx, validate_claim, resolve_entity). However, there is some inconsistency: single-word names like 'forget' and 'random' mix with multi-word names, and a few names use different structures (e.g., bet_research as noun_noun, random_by_category as adjective_preposition).

Tool Count3/5

32 tools is on the high side for a single server, covering a broad range of functionalities from data queries to betting and memory. While the number might be justified by the platform's scope, it feels heavy, and the server name 'Foodish' suggests a narrower food-focused purpose, creating a mismatch.

Completeness4/5

As a general data platform, the tool set is comprehensive, covering queries, research, entity resolution, memory, subscriptions, and various analytical tools. Minor gaps exist (e.g., no direct editing or upload capabilities), but the core workflows are well-supported. However, the server name 'Foodish' implies food-related tools, which are minimal, so completeness relative to the name is poor.

Resources