The Cure Protocol

search_cure_evidence

Read-only

SEARCH THE T1D EVIDENCE LEDGER by words, track, evidence class, direction, stage, outcome rung, PMID or trial. Both directions are returned, with the publication gate for the result set. NEXT: trace_scientific_claim on any claim.

Input Schema

Name	Required	Description
`q`	No	Words to search for.
`pmid`	No	PubMed id.
`limit`	No	How many claims.
`nctId`	No	Trial id.
`stage`	No	Disease stage.
`track`	No	A, B, C, D, E or unassigned.
`cursor`	No	Opaque cursor. Pass _meta.pagination.nextCursor from the previous call unchanged to get the next page; omit it to start at the beginning.
`offset`	No	Pagination offset.
`direction`	No	supports, contradicts or neutral.
`evidenceClass`	No	E1 to E5.
`outcomeCategory`	No	Outcome ladder rung id.

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

addedInput schema / properties / cursor

Added value: +{
+  "description": "Opaque cursor. Pass _meta.pagination.nextCursor from the previous call unchanged to get the next page; omit it to start at the beginning.",
+  "maxLength": 200,
+  "type": "string"
+}

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"
+}

Changed9 schema fields changedOct 24, 2026
- addedInput schema / properties / direction / maxLength
```
Added value: +20000
```
- addedInput schema / properties / evidenceClass / maxLength
```
Added value: +20000
```
- addedInput schema / properties / nctId / maxLength
```
Added value: +20000
```
- changedInput schema / properties / offset / maximum
```
Previous value: -9007199254740991New value: +100000
```
- addedInput schema / properties / outcomeCategory / maxLength
```
Added value: +20000
```
- addedInput schema / properties / pmid / maxLength
```
Added value: +20000
```
- addedInput schema / properties / q / maxLength
```
Added value: +500
```
- addedInput schema / properties / stage / maxLength
```
Added value: +20000
```
- addedInput schema / properties / track / maxLength
```
Added value: +20000
```
AddedOct 19, 2026

TDQS

A3.8/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds genuine behavioral context beyond that: results return both supporting and contradicting directions rather than one-sided hits, and the result set is subject to a 'publication gate', which warns the agent that results may be filtered by a gating rule. It stops short of explaining what that gate filters on.

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 short, front-loaded sentences with zero filler: purpose, then output behavior, then next step. The uppercase 'SEARCH' and 'NEXT:' markers make the operation and the routing hint scannable.

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 11 optional params, an output schema, and annotations, the description covers the key gaps: what corpus is searched, that both evidence directions are returned, and that a publication gate applies. Pagination is left to the schema's cursor documentation, which is adequate; only the meaning of the publication gate is left unexplained.

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 description coverage is 100% and every parameter is documented there, so baseline 3 applies. The description names the major filter facets, which only echoes the schema rather than adding format, matching semantics, or interaction rules (e.g., how q combines with direction or evidenceClass); it says nothing about limit, cursor or offset.

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 and resource ('SEARCH THE T1D EVIDENCE LEDGER') and enumerates the filterable facets (track, evidence class, direction, stage, outcome rung, PMID, trial), so an agent knows exactly what can be queried. It does not distinguish itself from close siblings like search_literature, search_world_trials or list_claims, so sibling differentiation is only partial.

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?

'NEXT: trace_scientific_claim on any claim' gives a concrete follow-on step, which is useful routing. However, there is no statement of when to use this vs. search_literature/search_world_trials (which appear to search other corpora) or list_claims, and no exclusions or prerequisites.

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?