Cochrane Medical Reviews

search_clinical_trials

Search clinical trials related to a health condition via PubMed.

Finds clinical trial publications matching the condition and optional
intervention. Returns trial titles, authors, and PubMed IDs.

Args:
    condition: The health condition or disease (e.g. 'type 2 diabetes',
        'breast cancer', 'depression').
    intervention: Optional treatment or intervention to include in search
        (e.g. 'metformin', 'cognitive behavioral therapy').
    limit: Maximum number of results to return (default 20, max 100).

Input Schema

TableJSON Schema

Name	Required	Description	Default
`limit`	No
`condition`	Yes
`intervention`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

TDQS

A4.5/5.0

Behavior4/5

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

With no annotations, the description carries full behavioral burden. It discloses the search source (PubMed), the return fields, and the limit parameter with default and max values. This gives meaningful insights into tool behavior. It does not mention ordering, error handling, or result filtering details beyond condition/intervention, but for a read-only search tool, the provided transparency is adequate.

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 concise and well-structured: an opening summary, a brief elaboration, and a clear Args section. Each sentence adds value, with examples and defaults included. There is no fluff, and the structure makes it easy for an agent to parse.

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?

The description covers purpose, parameter semantics, and return fields. An output schema exists to handle return structure, so that is not a gap. It does not mention edge cases like empty results or sorting, but for a simple search tool, the description is adequate. Sibling names provide additional context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate for missing parameter details. It does so effectively: condition and intervention come with concrete examples, and limit includes default and max values. Every parameter is semantically explained, fully covering the gaps left by the schema.

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 searches clinical trials related to a health condition via PubMed, with an optional intervention. It distinguishes itself from sibling tools (search_reviews, get_review_detail) by specifying clinical trials and PubMed. Return fields (titles, authors, PubMed IDs) further reinforce the purpose.

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?

The description clearly implies when to use the tool: to find clinical trial publications for a condition and optional intervention. It does not explicitly compare with sibling tools or state when not to use it, but the context is clear enough for an agent to select it appropriately. Lacks explicit alternatives or exclusions, so not a 5.

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

All Cochrane Medical Reviews tools Inspect

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

A4.5/5.0

Disambiguation5/5

Each tool targets a distinct resource and action: search_reviews finds reviews, get_review_detail retrieves a specific review's details, and search_clinical_trials searches for trial publications. There is no overlap in purpose, and clear usage flow is evident from descriptions.

Naming Consistency5/5

All tools follow a consistent verb_noun pattern with lowercase and underscores: search_reviews, search_clinical_trials, get_review_detail. The verbs 'search' and 'get' are appropriate for their actions, and the naming is predictable across the set.

Tool Count4/5

Three tools is at the lower bound of the well-scoped range. The server covers the core needs for searching and retrieving reviews, plus a trial search, but feels slightly thin given the broader medical research domain. Still, each tool earns its place and the count is reasonable for a focused server.

Completeness3/5

The review lifecycle is complete (search and get detailed). However, clinical trial search returns only metadata with no way to retrieve full trial details, leaving a potential dead end for agents needing more information. The domain is also somewhat ambiguous since the server name focuses on reviews but includes trials, making coverage feel incomplete.

Resources

Need Help?