Skip to main content
Glama

Ensembl

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

A4.8/5.0
Behavior5/5

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

The description transparently explains the tool's behavior, including routing, data fetching, grounding, and refusal behavior. It also discloses the cost of one extra LLM call, which is not evident from annotations alone.

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

Conciseness4/5

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

The description is somewhat long but each sentence serves a distinct purpose: defining the mode, explaining the mechanism, describing outputs, and giving usage guidance. It is structured well, though slightly repetitive in emphasizing grounding and high-stakes use.

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?

Even without an output schema, the description fully specifies the return shape including answer, evidence, confidence, source, fetched_at, and refusal_reason, along with all refusal reason enum values. This makes the tool's behavior complete and predictable for an agent.

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?

The schema covers all parameters and aliases, and the description adds value by clarifying that the question should be in natural language and that query, q, prompt, text, and input are accepted aliases. No parameter semantics are left ambiguous.

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: a hallucination-resistant answer mode for high-stakes reads. It explicitly distinguishes itself from sibling tools like ask_pipeworx by emphasizing grounded extraction from tool results.

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 gives explicit usage guidance: use when answers will be quoted, cited, or acted on, and prefer ask_pipeworx for casual lookups. It also explains the extra LLM call cost, making the trade-off clear.

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

All Ensembl 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

A3.6/5.0
Disambiguation2/5

There is heavy overlap in the ask_pipeworx family (ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, deep_research, bet_research, validate_claim) — several are near-identical 'route a natural-language question to a source' tools differing only by small qualifiers. ai_visibility_check vs scan_competitor_ai_presence and entity_profile vs compare_entities vs recent_changes also blur together. An agent could easily misselect among these.

Naming Consistency4/5

The dominant convention is snake_case verb_noun/noun_verb (list_subscriptions, scan_dependency, validate_claim, resolve_entity) which is fairly consistent, but there are several bare single-word verbs (lookup, sequence, variation, vep, xrefs, recall, remember, forget) that break the pattern. No camelCase is present, so the inconsistency is minor rather than chaotic.

Tool Count2/5

38 tools is heavy, and the overwhelming majority (~31) are Pipeworx meta-tools (subscriptions, memory, feedback, trend, discovery, llms.txt generation) that have nothing to do with the server's declared Ensembl identity. Only about 7 tools are actually genomics-related, so the count is inflated by off-domain additions that dilute the surface.

Completeness2/5

For the Ensembl domain, the surface covers gene lookup, symbol resolution, sequence retrieval, orthologs, SNPs, variant effect prediction, and xrefs — but misses major Ensembl capabilities like gene trees/families, regulatory features, comparative/multi-species alignments, expression data, phenotypes, GO/ontology annotations, and region/overlap queries. Conversely the Pipeworx tools are complete for their own domain but irrelevant here, leaving the declared domain notably incomplete.

Resources