Skip to main content
Glama

Emdb

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 5,798 across 1517 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.

Schema Changelog

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

  1. First observed

TDQS

A4.7/5.0
Behavior5/5

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

The description discloses refusal behavior with enumerated refusal_reason values, the evidence/verbatim-quote return contract, and the fact that it makes one extra LLM call. These traits go well beyond the annotations (read-only, idempotent) and tell the agent exactly what to expect for grounded answers.

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?

Dense but front-loaded: the first clause states the mode and stakes, then flows from routing to output contract to refusal contract to usage guidance and cost tradeoff. No sentence is filler; the length is justified by the tool's complexity.

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 no output schema, the description provides the field-level return shape, refusal_reason enum, and success/error split, plus the cost/routing context. It is complete enough for an agent to select and invoke the tool correctly in high-stakes scenarios.

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 every parameter is an alias for 'question' with descriptions, so the schema already carries the semantic burden. The description's focus is on usage rather than parameter behavior, so it adds no extra parameter-level meaning beyond the schema.

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 by naming the tool as a 'hallucination-resistant answer mode,' then explicitly contrasts it with ask_pipeworx: same routing, but it 'EXTRACTS the answer using ONLY what the tool result contains.' This gives a specific verb, resource, and a clear differentiation from its closest sibling.

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?

Explicit when-to-use and when-not: use when the answer will be quoted, cited, or acted on and facts must not be invented; prefer ask_pipeworx for casual lookups because of the extra LLM call. It even names the alternative tool and the tradeoff.

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

All Emdb 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

A3.7/5.0
Disambiguation2/5

Multiple tool clusters have overlapping purposes: ask_pipeworx, ask_pipeworx_beta, and ask_pipeworx_grounded are near-identical (the beta is explicitly the same right now); five polymarket_* tools all surface opportunity/edge information; entity_profile, compare_entities, and recent_changes all cover company research. The descriptions are detailed, but an agent can easily misselect between similar tools.

Naming Consistency4/5

All tool names use consistent snake_case and are descriptive, with clear prefix patterns for prediction-market tools (polymarket_*) and the router variants (ask_pipeworx_*). Some names are verb-noun while others are noun-phrases, but the convention is uniformly underscore-separated, with no camelCase or other mixing.

Tool Count2/5

33 tools is excessive for a coherent server, and the scope is sprawled across EMDB access, Pipeworx data routing, prediction markets, memory, subscriptions, and miscellaneous utilities. Even though each tool has a defined role, the sheer breadth and number make it feel like several servers' worth of functionality crammed into one.

Completeness2/5

The server's name suggests it should be focused on EMDB, but only two tools (get_map, search_maps) cover that domain — no browsing, filtering, or extended metadata beyond basic fields. Meanwhile, the bulk of the surface is devoted to unrelated Pipeworx/platform features. For the stated purpose, the coverage is severely incomplete.

Resources