Mondo

Mondo Resolve Condition

mondo_resolve_condition

Read-onlyIdempotent

Resolve free-text condition/disease strings — e.g. a clinical trial registry's "conditions" field ("Carcinoma, Non-Small-Cell Lung"), or a drug label's Indications and Usage wording — onto the Mondo Disease Ontology (MONDO), via EBI OLS4 full-text search plus MyDisease.info cross-references. Accepts a batch (1-25) of condition strings. For each, returns the original wording verbatim, the best MONDO id + label, and a match_quality you can trust: "exact-label" (identical to the Mondo term's primary label), "exact-synonym" (identical to a listed exact synonym), "broader"/"narrower" (the string exactly names a parent or child term reached via the Mondo hierarchy, not the top full-text hit itself), or "fuzzy" (closest full-text match, not a confirmed exact term — treat with caution). Also carries xrefs (OMIM, Orphanet, DOID, UMLS, MeSH) for the matched id. A string with no plausible Mondo term returns match_quality "no-match" with the queries tried and the nearest candidates found, never a bare empty result. Set expand:true to also get the resolved term's descendant MONDO ids, for building a subtype-inclusive filter (e.g. "any subtype of non-small cell lung carcinoma").

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "conditions": [
        "Carcinoma, Non-Small-Cell Lung",
        "NSCLC Stage IV",
        "type 2 diabetes mellitus",
        "Carcinoid Tumors",
        "Ehlers-Danlos syndrome"
      ]
    },
    "name": "mondo_resolve_condition"
  }
}

Input Schema

Name	Required	Description	Default
`expand`	No	When true, also return the resolved term's descendant MONDO ids (all subtypes) for each result. Default false.
`conditions`	Yes	1-25 free-text condition/disease strings, e.g. ["Non-small Cell Lung Cancer", "type 2 diabetes mellitus"].

Schema Changelog

Changes observed during successful MCP inspections.

First observedSep 23, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Goes far beyond the readOnlyHint/idempotentHint annotations by defining the match_quality taxonomy (exact-label, exact-synonym, broader/narrower, fuzzy), guaranteeing no bare empty results on no-match, and describing returned xrefs and expand behavior. Rich, decision-relevant behavioral context.

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?

Dense and front-loaded: purpose and examples come first, followed by the match_quality taxonomy and no-match behavior. The match_quality list is long but earns its place because it drives user trust; a slightly tighter structure would be possible.

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?

With no output schema, the description carries the full burden of explaining return values — and it does: match_quality semantics, no-match fallback, xrefs, and expand. Nothing an agent needs to call or interpret results is left to guesswork.

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 practical meaning beyond the schema by explaining the effect of expand (descendant MONDO ids for subtype-inclusive filters) and by providing realistic example condition strings that clarify what counts as free-text input.

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?

States a specific verb ('Resolve') and resource (Mondo Disease Ontology), and sharply differentiates itself from generic resolution tools by targeting condition/disease strings. Concrete use cases (clinical trial registry conditions, drug label Indications wording) make its niche unmistakable.

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?

Gives clear contexts for use: clinical trial registry conditions field, drug label wording, and subtype-inclusive filters via expand. However, it doesn't explicitly name sibling resolve_entity as an alternative or state when not to use this tool.

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

All Mondo 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.