Skip to main content
Glama

Openfda

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. Added

TDQS

A4.7/5.0
Behavior5/5

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

Even though annotations already mark it read-only, idempotent, and open-world, the description adds valuable behavioral detail: it returns evidence with verbatim quotes, refuses when the data doesn't directly answer, enumerates refusal reasons, and discloses the extra LLM call cost. This exceeds what annotations alone provide and does not contradict them.

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 dense but every sentence earns its place: purpose, routing behavior, return format, refusal behavior, use cases, and cost comparison. The most important distinguishing trait (grounded, hallucination-resistant) is front-loaded.

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 complex tool with no output schema, the description compensates fully by specifying the exact success and refusal response shapes, source grounding, and when to prefer the sibling tool. An agent has enough information to select, invoke, and interpret results.

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%, with a clear description for the 'question' parameter and its aliases. The tool description adds no parameter-level meaning beyond the schema, so a 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 states a specific, differentiated purpose: a hallucination-resistant answer mode that routes like ask_pipeworx but extracts answers only from tool results. It clearly identifies the resource, the behavior, and how it differs from its sibling ask_pipeworx, so an agent can distinguish it without opening schemas.

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 when-to-use guidance ('whenever an answer will be quoted, cited, or acted on'), gives concrete domain examples, and explicitly steers casual lookups to ask_pipeworx due to the extra LLM call. This is strong usage routing.

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

All Openfda 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

A4/5.0
Disambiguation4/5

Most tools have distinct names and purposes, but the large number of meta-tools (e.g., ask_pipeworx variants, deep_research) and overlapping research/scanning tools (entity_profile, compare_entities, recent_changes) could cause confusion. An agent may need to carefully read descriptions to choose correctly.

Naming Consistency3/5

Snake_case is prevalent but not universal. FDA tools are consistently named with 'fda_' prefix, but there are single-word verbs (remember, recall), camelCase is absent, and some tool names are long and descriptive (scan_competitor_ai_presence). The mix of patterns is readable but not highly consistent.

Tool Count3/5

43 tools is high and includes both dedicated tools and meta-tools that can access thousands more. There is redundancy (e.g., FDA data can be retrieved via fda_drug_approvals or ask_pipeworx). The scope is broad, but many tools could be consolidated. Count feels borderline excessive for the apparent purpose.

Completeness4/5

FDA coverage is excellent with tools for approvals, labels, events, recalls, shortages, warning letters, etc. Other domains (financial, betting, npm) are covered by meta-tools, providing breadth. However, dedicated non-FDA tools are sparse, and the server relies heavily on the universal query tools for completeness.

Resources