Jean by Melad Labs

design_rbs

Design a 5'UTR (Shine-Dalgarno + spacer) in front of a CDS to hit a target translation-initiation strength (SC-08 engine, Turner-2004 folding).

Input Schema

Name	Required	Description
`cds`	No	the CDS starting at its start codon; unset = the open record's sequence.
`_files`	No	The project: record references shaped like _subject. Their records become library documents a tool names in sequences/parts/document; a trace or alignment is found by file name.
`_subject`	No	The record to act on: exactly one of sequence, accession (+source), sample (an id from list_samples) or file ({name, text} or {name, base64}); record_index picks one record of several.
`upstream`	No	upstream context 5' of the UTR (engine default when unset). Advanced.
`target_strength`	Yes	target relative strength, on the model's own scale — 1 is as strong as its reference site, and real sites do score above it.

Output Schema

Name	Required	Description
`sd`	Yes	the Shine-Dalgarno core
`utr`	Yes	the designed 5'UTR
`full`	Yes	UTR + CDS
`dgTotal`	Yes	the predicted total free energy of translation initiation (ΔG_total, kcal/mol) for the designed site; null when the model could not fold it
`spacing`	Yes	SD→start spacing
`onTarget`	Yes	whether the target strength was reachable
`relStrength`	Yes	achieved relative strength
`achievableMax`	Yes	the strongest relative strength any candidate site reached in this search, which bounds what a target above it can get
`achievableMin`	Yes	the weakest relative strength any candidate site reached in this search, which bounds what a target below it can get

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 25, 2026
- addedOutput schema / properties / dgTotal / x-unit
```
Added value: +"kcal/mol"
```

Changed4 schema fields changedOct 21, 2026

addedOutput schema / properties / achievableMax

Added value: +{
+  "description": "the strongest relative strength any candidate site reached in this search, which bounds what a target above it can get",
+  "type": [
+    "number",
+    "null"
+  ]
+}

addedOutput schema / properties / achievableMin

Added value: +{
+  "description": "the weakest relative strength any candidate site reached in this search, which bounds what a target below it can get",
+  "type": [
+    "number",
+    "null"
+  ]
+}

addedOutput schema / properties / dgTotal

Added value: +{
+  "description": "the predicted total free energy of translation initiation (ΔG_total, kcal/mol) for the designed site; null when the model could not fold it",
+  "type": [
+    "number",
+    "null"
+  ]
+}

changedOutput schema / required

Previous value: -[
-  "utr",
-  "sd",
-  "full",
-  "spacing",
-  "relStrength",
-  "onTarget"
-]New value: +[
+  "utr",
+  "sd",
+  "full",
+  "spacing",
+  "relStrength",
+  "onTarget",
+  "dgTotal",
+  "achievableMin",
+  "achievableMax"
+]

First observedOct 20, 2026

TDQS

A3.6/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false, and openWorldHint=false, so the safety profile is partly covered. The description adds useful algorithmic context (SC-08 engine, Turner-2004 folding) and says what is being designed, but does not clarify whether it writes a record, only emits a sequence, or what side effects occur.

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?

It is a single, front-loaded sentence with no wasted words. The parenthetical engine details are compact and directly relevant to the task.

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?

Given the rich input schema, annotations, and an output schema, the description covers the core purpose and modeling context well enough to call the tool. The main remaining gap is routing guidance versus score_rbs and other design tools, but that is more a usage-guideline issue than a missing core fact.

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 has a schema description. The tool description adds only high-level framing for CDS and target_strength and does not explain upstream, _files, or _subject beyond what the schema already provides, so the baseline 3 is appropriate.

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 description gives a specific verb ('Design') and resource ('5'UTR (Shine-Dalgarno + spacer) in front of a CDS'), plus the target outcome ('target translation-initiation strength'). It is clearly distinct from a scoring tool like score_rbs, but it does not explicitly name sibling tools or state the boundary against them.

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?

Usage is implied by 'Design ... to hit a target translation-initiation strength' — an agent can infer this is for constructing an RBS rather than evaluating one. However, there is no explicit when-to-use guidance, no comparison to score_rbs, and no stated prerequisites or exclusions.

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

All Jean by Melad Labs 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?