Skip to main content
Glama

Opencellid

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 5,801 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. Added

TDQS

A4.4/5.0
Behavior5/5

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

Beyond the annotations (readOnly, openWorld, idempotent), the description discloses the tool's refusal behavior with specific refusal_reason values, its method of extracting answers only from tool results, and the extra LLM call cost. These behavioral details are not present in annotations and enhance transparency about the tool's operation and constraints.

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

Conciseness3/5

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

The description is longer than necessary and contains repetition, particularly the phrase 'Same routing as ask_pipeworx — picks the right tool from 5,801 across 1517 sources, fills arguments, fetches the data' appears twice (once in the main body and once in the return/refusal explanation). While structured with key sections, the redundancy detracts from conciseness.

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?

The description provides a complete picture: it explains the tool's purpose, usage context, return format (including refusal reasons), and differentiates it from the sibling ask_pipeworx. Since there is no output schema, the detailed return structure and refusal scenarios fill that gap. Minor omission: it does not mention any limitations beyond the extra cost, but the context is otherwise sufficient.

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?

The input schema has 100% coverage with each parameter described as an alias for 'question,' and the main parameter 'question' is clearly explained. However, the tool description itself adds no additional semantic detail beyond the schema, so the parameter semantics are adequate but not enhanced.

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 clearly states the tool's purpose as a 'hallucination-resistant answer mode for high-stakes reads' and differentiates it from the sibling ask_pipeworx by emphasizing grounded extraction from tool results and explicit refusal when data is not available. It also identifies the exact scenario for its use, making the purpose unambiguous.

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?

The description explicitly provides usage guidance: 'Use whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts' and 'prefer ask_pipeworx for casual lookups.' It also notes the extra LLM call cost, giving clear conditional guidance for choosing between this tool and its sibling.

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

All Opencellid 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
Disambiguation3/5

While many tools have distinct purposes, there is significant overlap among the Pipeworx query tools: ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, deep_research, and suggest_questions all route questions to the same underlying sources. Also, several Polymarket analysis tools (polymarket_arbitrage, polymarket_edges, polymarket_edge_tracker, polymarket_fill_risk) have overlapping purposes of finding and analyzing betting edges. This overlap could cause misselection, though the detailed descriptions provide some disambiguation.

Naming Consistency3/5

The naming is mostly readable but mixes conventions: pipeworx tools use snake_case (ask_pipeworx, pipeworx_feedback), while the prediction market tools use camelCase (polymarket_edges, polymarket_edge_tracker, polymarket_arbitrage). Verbs vary widely: ask, get, scan, generate, recall, remember, resolve, search, subscribe, unsubscribe, validate. There's a mix of domain-specific prefixes and generic actions without a clear uniform pattern.

Tool Count2/5

33 tools is a very large surface for an MCP server, even one covering a broad domain. While the server claims to cover many data sources (financial, pharma, economics, prediction markets, cell towers, etc.), the high count risks cognitive overload and makes it hard for an agent to discover the right tool. Many tools appear to be meta-tools (suggest_questions, discover_tools, remember/recall/forget) that add to the count without adding core domain operations.

Completeness4/5

The server covers a wide range of functionality: data lookup, entity resolution, research, prediction market analysis, memory management, subscriptions, and even niche features like AI visibility checking and llms.txt generation. Given the breadth, most use cases have coverage. However, the completeness is uneven—the OpenCellID tools (cells_in_area, get_cell) are very minimal with just two basic lookups and no batch/history features, while the Pipeworx side has extensive coverage. Some operations like updating or deleting entities are absent, but that may not be expected for a read-heavy data server.

Resources