Skip to main content
Glama
Sign In

biomedmcp

by io.github.unibio-intelligence
OverviewDiscussionsAdmin

Search clinical trials

search_trials
Read-onlyIdempotent

Search clinical trials (ClinicalTrials.gov, NCI) by condition, intervention, phase and recruitment status. Read arms, eligibility or outcomes with get_record(entity=trial). Does not assess an individual's eligibility. e.g. {"query":"familial hypercholesterolemia","filters":{"status":"RECRUITING"}}

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "query": "<query>"
    },
    "name": "search_trials"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNo
queryYes
cursorNonext_cursor from the previous page.
outputNosummary trims excerpts; full keeps source fields. Omitted evidence stays recoverable.summary
filtersNo
freshnessNofresh bypasses the cache.cached_if_fresh

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare this is a safe, read-only, idempotent, open-world lookup, so the description carries a lighter burden. It still adds real context beyond them: which registries are queried and the fact that results are summary-level, with arms/eligibility/outcomes only reachable through get_record. It does not discuss caching behavior beyond the schema's freshness enum or any rate limits, which keeps it below the top mark.

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?

Three sentences plus a compact JSON example, with the core capability front-loaded before the sibling pointer and the scope exclusion. Every element earns its place: the example conveys argument shape more efficiently than prose would.

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?

An output schema exists, so return shape needn't be described, and pagination (cursor) and cache behavior (freshness) are documented in the schema itself. The description covers purpose, sources, scope limits and a usage example, leaving only minor gaps such as the meaning of limit/output defaults.

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 50%, and the description partially compensates by naming the searchable facets (condition, intervention, phase, status) that map onto disease/query, drug, phase and status. The worked example clarifies the shape of query plus filters, but limit, cursor, output, freshness, source and gene get no added meaning in the prose. Adequate, not compensating fully for the coverage gap.

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 gives a specific verb and resource ('Search clinical trials') and pins the sources ('ClinicalTrials.gov, NCI'), plus the facets it can search on (condition, intervention, phase, recruitment status). It also draws a boundary against a named sibling by directing detail reads to get_record(entity=trial), so an agent can distinguish this from search_records or search_literature without opening a schema.

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 states the search context (by condition, intervention, phase, status), points to the alternative for deeper data ('Read arms, eligibility or outcomes with get_record'), and includes an explicit exclusion ('Does not assess an individual's eligibility'). The exclusion is a scope caveat rather than a route to another tool, so the when-not guidance is slightly incomplete, but the routing advice is clear.

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

All biomedmcp toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources