Skip to main content
Glama

LiveDataLink

by io.github.blackboxfoundry

clinical_site_selector

Read-onlyIdempotent

One-call clinical-trial-activity + local-specialist-availability read for a medical condition in a US geography - the question a trial sponsor, CRO, or site-feasibility analyst asks before choosing where to run a study. Joins three keyless public sources: ClinicalTrials.gov (exact count of RECRUITING trials for the condition, scoped to the geography and compared to the national total, plus the top lead sponsors and phase mix from the recruiting sample), the NPPES NPI Registry (local specialist availability - how many providers carry a specialty taxonomy relevant to the condition in the area, across physicians and NPs/PAs/pharmacists/RNs in the field), and optionally US Census ACS population context for the state (needs a Census key; degrades gracefully). The condition is mapped to a provider specialty heuristically; pass an explicit 'specialty' to override. Returns a readable brief with a headline banding trial activity (HIGH/MODERATE/LOW/NONE) and specialist availability. A source that fails is noted, not fatal. INFORMATIONAL research / site-feasibility synthesis, NOT medical advice or a directive to enroll in any trial.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
cityNoOptional city to further localize the trial-location and provider search (e.g. 'Houston'); use with state.
stateNoOptional 2-letter US state to scope trial and provider counts (e.g. 'TX'). Omit for a national read.
conditionYesMedical condition / disease to evaluate (e.g. 'melanoma', 'type 2 diabetes', 'Alzheimer disease').
specialtyNoOptional NPPES specialty taxonomy keyword to override the condition-to-specialty mapping (e.g. 'Cardiology', 'Endocrinology').

TDQS

A4.7/5.0
Behavior5/5

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

The description goes far beyond the readOnlyHint annotations by disclosing the three keyless sources, heuristic condition-to-specialty mapping, graceful degradation of Census data, non-fatal source failures, and the informational-not-medical-advice caveat. These behaviors materially affect how an agent should interpret results.

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?

Every sentence earns its place: purpose, sources, mapping behavior, return format, failure handling, and disclaimer. The description is dense but not redundant, and the core purpose is front-loaded before the detailed source enumeration.

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 composite tool with no output schema, the description covers what is returned (readable brief with HIGH/MODERATE/LOW/NONE banding and specialist availability), how failures are handled, and the optional Census key limitation. An agent has enough information to decide when to call it and what to expect.

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?

Schema coverage is 100%, so the baseline is 3, but the description adds real semantic context: condition is heuristically mapped to a specialty, the specialty parameter overrides that mapping, state omission yields a national read, and city should be used with state. This is meaningful guidance beyond the property descriptions.

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 composite resource — a clinical-trial-activity and provider-availability read for a condition in a US geography — and identifies the decision context. It also distinguishes itself from sibling single-source tools by emphasizing the one-call synthesis and the headline banding output.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives clear context: a trial sponsor, CRO, or site-feasibility analyst before choosing where to run a study. It does not explicitly name alternatives or say when not to use it, but the intended use case is specific enough to guide selection.

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

All LiveDataLink 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

B3.2/5.0
Disambiguation2/5

Many tools overlap heavily across domains: caselaw_search vs court_case_search vs court_opinion_search, caselaw_citation_lookup vs court_citation_resolver, and a cluster of company due-diligence tools (company_trust_check, counterparty_risk_score, entity_dossier, issuer_diligence_dossier, kyb_aml_evidence_case_file) that all screen a company for sanctions/risk/standing. With 290 tools, an agent will frequently face multiple equally plausible choices for the same user intent.

Naming Consistency3/5

The vast majority of tools follow a clean domain-prefix + snake_case pattern (census_, eia_, fmcsa_, npi_, cfpb_, etc.), but there are notable exceptions: entity_resolve and resolve_entity are reversed duplicates, reg_search (Federal Register) sits next to reg_cfr_search (CFR) with confusingly similar names, and carrier_monitor_recheck deviates from the carrier_vetting_* family.

Tool Count1/5

290 tools is an extreme count under any rubric, far exceeding even the 50+ threshold for the lowest score. While the group-filtering mechanism and meta-tools like list_tool_groups and search_available_datasets mitigate the practical burden, the raw surface is still massively oversized for an agent to select from accurately and efficiently.

Completeness4/5

For a read-only data-aggregation server, coverage is remarkably comprehensive across 59 domains, and generic fallbacks like cdc_dataset_query, eia_series_lookup, fred_observations, and bls_series prevent most dead ends. Minor gaps exist (a single GitHub tool, demo-only property_lookup coverage, no write/update operations anywhere), but the stated data-access purpose is well served.

Resources