CliniAtlas Evidence

Ask CliniAtlas

ask_cliniatlas

Full CliniAtlas answer to a clinical or research question, with numbered citations.

    Searches the literature, guidelines and EMA documents and writes a cited answer, the
    same answer cliniatlas.com gives. Uncited parts are reported through grounding.
    Each call starts a background answer job, and a completed answer uses one of the
    user's daily full answers (see free_answers_remaining_today), so check
    search_evidence_library first and use a published answer when one matches. Usually takes 35 to 50 seconds: if status is
    "running", call get_cliniatlas_answer with job_id. Do not include patient
    identifiers. For literature research and education, not individual care decisions.

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": {
      "question": "<question>"
    },
    "name": "ask_cliniatlas"
  }
}

Input Schema

Name	Required	Description	Default
`locale`	No
`question`	Yes

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

AddedOct 1, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Adds substantial behavior beyond the annotations: each call starts a background job, consumes one of the user's daily full answers, typically takes 35-50 seconds, and reports uncited portions through grounding. These quota, latency and async-lifecycle facts materially change how an agent should invoke it.

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?

Front-loaded with purpose, then workflow, then constraints; most sentences carry actionable information. A few clauses (the cliniatlas.com reference, the grounding remark) are slightly tangential but not wasteful.

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?

For an async, quota-consuming, open-world tool the description covers lifecycle, cost, timing, safety and output grounding, and an output schema exists so return values need not be described. The only meaningful omission is the locale parameter's semantics.

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 0%, so the description must carry the parameter burden. It adds the important constraint that the question must not include patient identifiers, but it never explains the locale parameter (format, default, or effect) and gives no detail on question length or phrasing beyond the schema's min/max.

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 first sentence names a specific verb+resource: produce a full, cited CliniAtlas answer to a clinical or research question. It also states the source corpus (literature, guidelines, EMA documents), which distinguishes it clearly from sibling lookup/search tools like lookup_pubmed and search_evidence_library.

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?

Explicit routing rules are given: check search_evidence_library first and use a published answer when one matches, and if status is "running" call get_cliniatlas_answer with job_id. It also names an exclusion (education/research, not individual care decisions), leaving little to inference.

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

All CliniAtlas Evidence tools Inspect

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

Need Help?