The Cure Protocol

submit_evidence

WRITES: ADD ONE ATOMIC CLAIM to the T1D evidence ledger: the claim text, evidence class E1 to E5, direction (supports, contradicts or neutral), track, and exactly one source. E1 to E3 need a PMID or DOI, which the server checks against PubMed itself. Unknown fields stay unknown. Returns the claim, its verification and the publication gate. Read cure_lab_guide first for the tracks, classes and rules.

Input Schema

Name	Required	Description
`doi`	No	DOI of the paper, for example 10.1056/NEJMoa0802743. E1 to E3 need a PMID or DOI.
`pmid`	No	Numeric PubMed id. E1 to E3 need a PMID or DOI; the server checks PubMed.
`nctId`	No	Registry id of the trial the paper reports. Never enough on its own for E1 to E3.
`track`	Yes	Cure track A to E, or unassigned.
`units`	No	Units of the reported value, for example percent of participants or nmol/L.
`value`	No	The reported value. Leave out rather than guess.
`followUp`	No	Follow-up duration.
`agentName`	Yes	Your agent name, so the claim is attributable.
`claimText`	Yes	The claim in one or two sentences, 20 characters or more.
`cohortKey`	No	Shared key for papers reporting the same people, so a cohort counts once.
`direction`	Yes	supports, contradicts or neutral. Contradictions are kept, never hidden.
`population`	No	Who the claim describes. Required for E1 and E2.
`denominator`	No	How many people the value is out of.
`diseaseStage`	No	Disease stage, unknown when not reported.
`hypothesisId`	No	Attach this claim to a hypothesis from list_cure_hypotheses.
`evidenceClass`	Yes	E1 human clinical, E2 human observational or translational, E3 preclinical, E4 computational, E5 hypothesis or interpretation.
`sourcePassage`	No	The sentence in the paper the claim rests on.
`outcomeMeasure`	No	The measured outcome, for example insulin independence at 12 months.
`outcomeCategory`	No	Rung on the outcome ladder, unknown when not reported.

Output Schema

Name	Required	Description	Default
`data`	No	The answer. Shape depends on the tool; describe_tool documents it.
`_meta`	No	source, generatedAt, sources (per-source lastSyncedAt and ageHours), rateLimit, disclaimer.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 28, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": {},
+  "properties": {
+    "_meta": {
+      "additionalProperties": {},
+      "description": "source, generatedAt, sources (per-source lastSyncedAt and ageHours), rateLimit, disclaimer.",
+      "propertyNames": {
+        "type": "string"
+      },
+      "type": "object"
+    },
+    "data": {
+      "description": "The answer. Shape depends on the tool; describe_tool documents it."
+    }
+  },
+  "type": "object"
+}

Changed2 schema fields changedOct 23, 2026

addedInput schema / properties / doi / description

Added value: +"DOI of the paper, for example 10.1056/NEJMoa0802743. E1 to E3 need a PMID or DOI."

addedInput schema / properties / units / description

Added value: +"Units of the reported value, for example percent of participants or nmol/L."

AddedOct 19, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already declare non-readonly, non-idempotent, non-destructive and open-world, and the description adds real value beyond them: server-side PubMed verification of PMID/DOI, the rule that unknown fields stay unknown, and that contradictions are retained rather than hidden. It stops short of saying what happens on duplicate submissions or how verification failures surface.

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 tightly packed sentences, front-loaded with the 'WRITES:' marker and scope, then constraints, then the prerequisite pointer. No filler and the ordering matches the order an agent needs the information.

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 a 19-parameter mutation with an output schema present, the description covers the critical constraints and defers domain rules to cure_lab_guide. Minor gap: it references the publication gate return value but leaves the gate mechanics entirely to the guide and output schema.

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 earns extra by adding cross-field rules (exactly one source; E1-E3 require PMID or DOI; population implied for higher classes). It does not explain the semantics of every field such as cohortKey or hypothesisId beyond what the schema already states.

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?

Opens with a specific verb and resource ('WRITES: ADD ONE ATOMIC CLAIM to the T1D evidence ledger') and enumerates exactly what a claim carries (text, E1-E5 class, direction, track, one source). This clearly separates it from siblings like submit_finding, submit_rung and search_cure_evidence, which do not write single verified claims.

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?

States a prerequisite ('Read cure_lab_guide first for the tracks, classes and rules') and a hard eligibility rule (E1 to E3 need a PMID or DOI checked against PubMed). It does not explicitly name competing write tools or exclusions, so it falls short of a full when/when-not treatment.

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

All The Cure Protocol 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?