Skip to main content
Glama
Sign In

The Cure Protocol

by com.negativeresistance
OverviewDiscussionsAdmin

run_twin_experiment

Read-only

Integrate a declared mass-action model with unperturbed controls, scheduled parameter changes, numerical verification, sensitivity bounds and optional observations. Read twin_experiment_guide first. Returns a replay manifest and raw errors, never a disease cure claim. No remote code or learned-model weights are downloaded or executed.

Input Schema

NameRequiredDescriptionDefault
armsYes1 to 4 intervention arms: {id, startStep, rateMultipliers {reactionId: 0 to 10}}. A baseline arm is added automatically.
modelYesMass-action model: {id, version, context, scope, provenance, timeUnit, concentrationUnit, species[{id, initial}], reactions[{id, rate, reactants, products}], conservedPools}. Up to 16 species and 24 reactions. See twin_experiment_guide.
stepsNoNumber of output time steps, 4 to 100. Default 40.
datasetNoOptional dataset declaration for the observations: {id, citation (https), sha256, kind, split, independentOfModelFit}.
durationYesSimulated time span in model.timeUnit, greater than 0 and at most 1000. Example 48.
uncertaintyNoUp to 3 reactions with {reaction, low, high} rate bounds for sensitivity runs.
observationsNoUp to 200 measured values {arm, step, species, value} in model.concentrationUnit, compared against the simulation.

Output Schema

NameRequiredDescriptionDefault
dataNoThe answer. Shape depends on the tool; describe_tool documents it.
_metaNosource, generatedAt, sources (per-source lastSyncedAt and ageHours), rateLimit, disclaimer.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • 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"
+}
  2. Changed7 schema fields changed
    • addedInput schema / properties / arms / description
      Added value: +"1 to 4 intervention arms: {id, startStep, rateMultipliers {reactionId: 0 to 10}}. A baseline arm is added automatically."
    • addedInput schema / properties / dataset / description
      Added value: +"Optional dataset declaration for the observations: {id, citation (https), sha256, kind, split, independentOfModelFit}."
    • addedInput schema / properties / duration / description
      Added value: +"Simulated time span in model.timeUnit, greater than 0 and at most 1000. Example 48."
    • addedInput schema / properties / model / description
      Added value: +"Mass-action model: {id, version, context, scope, provenance, timeUnit, concentrationUnit, species[{id, initial}], reactions[{id, rate, reactants, products}], conservedPools}. Up to 16 species and 24 reactions. See twin_experiment_guide."
    • addedInput schema / properties / observations / description
      Added value: +"Up to 200 measured values {arm, step, species, value} in model.concentrationUnit, compared against the simulation."
    • addedInput schema / properties / steps / description
      Added value: +"Number of output time steps, 4 to 100. Default 40."
    • addedInput schema / properties / uncertainty / description
      Added value: +"Up to 3 reactions with {reaction, low, high} rate bounds for sensitivity runs."
  3. Changed1 schema field changed
    • changedInput schema / properties / model / properties / timeUnit / enum
      Previous value: -[
-  "second",
-  "minute",
-  "hour"
-]New value: +[
+  "second",
+  "minute",
+  "hour",
+  "week"
+]
  4. Added

TDQS

A3.9/5.0
Behavior4/5

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

The description goes beyond the readOnlyHint/openWorldHint annotations by disclosing the safety posture ('No remote code or learned-model weights are downloaded or executed') and the epistemic boundary ('never a disease cure claim'), which matters for a scientific simulation. It also tells the agent what comes back (replay manifest, raw errors), though with an output schema present this is a bonus rather than a necessity.

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 sentences, front-loaded with the operation, then the prerequisite, then the return/limitation statement. Nothing is redundant and each sentence carries distinct information.

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?

For a complex nested-schema tool with an output schema, annotations, and a companion guide, the description covers what is run, what must be read first, what is returned, and what is explicitly off-limits. The only gap is sibling disambiguation from run_twin_benchmark, which is minor given the guide-first routing.

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 the nested model/arms/uncertainty/observations descriptions are already detailed. The prose in the tool description adds no parameter-level syntax or format information beyond what the schema provides, so baseline 3 applies.

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?

The verb 'Integrate' plus the resource 'a declared mass-action model' is specific and the enumerated activities (unperturbed controls, scheduled parameter changes, sensitivity bounds, optional observations) make the scope unambiguous. It does not, however, distinguish itself from the sibling run_twin_benchmark, so an agent cannot tell from this text alone which of the two simulation tools to pick.

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?

'Read twin_experiment_guide first' gives a useful prerequisite and the phrase 'declared mass-action model' implies a pre-built model input. Beyond that, there is no explicit when-to-use/when-not-to-use statement and no comparison against run_twin_benchmark or the guide tools.

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 toolsInspect
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