Skip to main content
Glama
berntpopp

hpo-link

by berntpopp
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Resolve HPO Cross-Reference

resolve_xref
Read-onlyIdempotent

Find the HPO terms that cross-reference an external CURIE such as NCIT, MEDDRA, UMLS, ICD-10, MONDO, DOID or ORPHA, returning paginated matches.

Instructions

Resolve an external cross-reference CURIE (UMLS/SNOMEDCT_US/NCIT/MEDDRA/ICD-10/ICD-9/MONDO/DOID/ORPHA) back to the HPO term(s) that cross-reference it. Returns matches[] plus a pagination block {total, returned, limit, offset, truncated, next_offset}; when truncated, next_commands carries a forward-page step (offset). Signature: resolve_xref(xref_id, limit=, offset=, response_mode=).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNoMax matches (default 25).
offsetNoRows to skip for forward paging (default 0).
xref_idYesAn external cross-reference CURIE (prefix:local) present in the selected HPO release, such as NCIT or MEDDRA, to resolve back to matching HPO terms.
response_modeNoVerbosity: minimal|compact|standard|full (default compact).compact

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.4.9
    • changedInput schema / properties / xref_id / description
      Previous value: -"An external cross-reference CURIE (prefix:local), e.g. UMLS/SNOMED/NCIT/MEDDRA, to resolve back to the HPO term(s) that cross-reference it."New value: +"An external cross-reference CURIE (prefix:local) present in the selected HPO release, such as NCIT or MEDDRA, to resolve back to matching HPO terms."
    • changedInput schema / properties / xref_id / examples
      Previous value: -[
-  "UMLS:C0036572",
-  "SNOMEDCT_US:263681008",
-  "NCIT:C4890"
-]New value: +[
+  "NCIT:C3754",
+  "MEDDRA:10022016"
+]
  2. Changed1 schema field changedv0.4.0
    • changedOutput schema / (root)
      Previous value: -{
-  "additionalProperties": true,
-  "properties": {
-    "_meta": {
-      "additionalProperties": true,
-      "type": "object"
-    },
-    "allowed_values": {
-      "type": "array"
-    },
-    "candidates": {
-      "type": "array"
-    },
-    "error_code": {
-      "type": "string"
-    },
-    "field": {
-      "type": "string"
-    },
-    "hint": {
-      "type": "string"
-    },
-    "hpo_version": {
-      "type": [
-        "string",
-        "null"
-      ]
-    },
-    "limit": {
-      "type": "integer"
-    },
-    "matches": {
-      "type": "array"
-    },
-    "message": {
-      "type": "string"
-    },
-    "next_offset": {
-      "type": "integer"
-    },
-    "offset": {
-      "type": "integer"
-    },
-    "recovery_action": {
-      "type": "string"
-    },
-    "retryable": {
-      "type": "boolean"
-    },
-    "returned": {
-      "type": "integer"
-    },
-    "success": {
-      "type": "boolean"
-    },
-    "total": {
-      "type": "integer"
-    },
-    "truncated": {
-      "type": "boolean"
-    },
-    "xref_id": {
-      "type": "string"
-    }
-  },
-  "type": "object"
-}New value: +null
  3. Changed1 schema field changedv0.1.1
    • changedInput schema / properties / xref_id / examples
      Previous value: -[
-  "UMLS:C0036572",
-  "SNOMEDCT_US:193046000",
-  "NCIT:C4890"
-]New value: +[
+  "UMLS:C0036572",
+  "SNOMEDCT_US:263681008",
+  "NCIT:C4890"
+]
  4. First observedv0.1.0

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, openWorld, and non-destructive behavior, so the safety profile is covered. The description adds genuinely useful context beyond the annotations: the return shape (matches[] plus a pagination block), the truncation flag, and the next_commands forward-page hint. It does not discuss rate limits or auth, but for a read-only lookup this is solid.

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?

Purpose is front-loaded in the first sentence and the pagination/return detail follows compactly. The trailing 'Signature:' line is largely redundant with the schema and could be dropped, but overall it is tight and well-ordered.

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?

With no output schema, the description usefully fills the gap by describing matches[] and the pagination block including truncation and next_commands behavior. For a single-required-param read-only lookup this is close to complete; only explicit alternative-tool routing is missing.

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 100%, so xref_id, limit, offset, and response_mode are all documented in the schema itself. The description's 'Signature:' line merely restates parameter names and adds no format or semantic detail beyond the schema, which is the expected baseline when the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (resolve) and resource (external cross-reference CURIE) with a clear direction 'back to the HPO term(s)', and enumerates the accepted prefixes (UMLS, SNOMEDCT_US, NCIT, MEDDRA, ICD-10, MONDO, DOID, ORPHA). The reverse-mapping direction implicitly separates it from the likely sibling map_cross_ontology, though no sibling is named explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description makes the use case inferable (you have an external CURIE and want the HPO terms referencing it), but it offers no explicit when-to-use/when-not guidance and does not name alternatives such as map_cross_ontology or resolve_term for the opposite direction.

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

Deploy Server

Other Tools