Skip to main content
Glama

Noodle Biomedical Literature Discovery MCP

by io.github.helena-bioinformatics

Search biomedical literature

search_biomedical_literature
Read-onlyIdempotent

Semantically search Noodle's public PubMed-derived biomedical corpus. Include known PMID, DOI, or PMCID identifiers in the query so they can act as exact anchors. Results are for literature discovery and professional review, not diagnosis or treatment.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
sortNoResult ordering: relevance-ranked, newest publication first, or oldest publication first.relevance
limitNoMaximum number of publications to return, from 1 to 25.
queryYesNatural-language literature question or exact PMID, DOI, PMCID, gene, variant, phenotype, HPO, or OMIM query. Include every known publication identifier when comparing or finding related papers.
cursorNoOpaque continuation cursor from the preceding response for the same query and sort order; omit for the first page.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryYes
resultsYes
has_moreNo
graph_usedNo
next_cursorNo
graph_versionNo
returned_countYes
usage_boundaryYes
contract_versionYes
searchable_fieldsYes
semantic_index_usedNo
graph_degraded_reasonNo
semantic_degraded_reasonNo

TDQS

A4.5/5.0
Behavior4/5

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

The description adds behavioral context beyond the annotations: the corpus is public and PubMed-derived, the search is semantic rather than keyword-only, identifiers anchor results, and results are not suitable for medical decisions. The readOnlyHint, idempotentHint, and destructiveHint are not contradicted.

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 front-loaded, purposeful sentences with no filler: the first states what the tool does, the second gives query-construction guidance, and the third sets scope/limitations. Every sentence earns its place.

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?

Given the annotations, full schema coverage, and presence of an output schema, the description covers all essential operational context: corpus scope, semantic-search behavior, identifier-anchoring strategy, and intended use limitations. Nothing an agent needs to call this tool correctly is missing.

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. The description adds value beyond the schema by telling agents to include known identifiers in the query as 'exact anchors,' which clarifies effective use of the query parameter. Other parameters (sort, limit, cursor) are already well documented in 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 uses a specific verb and resource: 'Semantically search Noodle's public PubMed-derived biomedical corpus.' This clearly differentiates the tool from siblings like get_publication_details or get_corpus_summary, which retrieve specific entities or summaries rather than perform corpus-wide semantic search.

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 gives explicit query guidance: include known PMID, DOI, or PMCID identifiers so they can act as exact anchors. It also states the appropriate context ('literature discovery and professional review') and excludes diagnosis or treatment, providing clear usage boundaries without naming sibling alternatives.

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

All Noodle Biomedical Literature Discovery MCP 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

A3.9/5.0
Disambiguation4/5

The search and corpus tools are clearly distinct, and the two detail and two neighborhood tools are parallel but differentiated by identifier type (PMID vs. Noodle work ID). The main ambiguity is that get_publication_details and get_work_details both retrieve full records, so agents must understand which identifier they have. support_helena is unrelated but unambiguously separated.

Naming Consistency4/5

Most tools follow a consistent snake_case get_<resource>_<scope> pattern, and search_biomedical_literature fits the retrieval theme. support_helena is a minor outlier because it uses a different action verb and target, but it does not break the overall naming style.

Tool Count5/5

Seven tools is well-scoped for a read-only literature discovery server: corpus summary, semantic search, two lookup modes, two neighborhood exploration modes, and one support action. The count feels intentional and each tool serves a distinct part of the discovery workflow.

Completeness4/5

The read-only discovery surface is largely complete with corpus metadata, search, detailed record retrieval, and neighborhood exploration. A minor gap is that direct retrieval is only by PMID or Noodle work ID, not by DOI/PMCID, though search can serve as a workaround.

Resources