Jean by Melad Labs

crispr_design_guides

Read-only

Design and score CRISPR guides on the subject — on/off-target scores, QC flags, and cloning-enzyme conflicts. Nuclease list comes from the real nuclease registry.

Input Schema

Name	Required	Description	Default
`_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.
`min_stem`	No	minimum self-complementary stem to report. In nt. Advanced.
`nuclease`	No	the nuclease (PAM + spacer length) to scan for. Values: SpCas9 (SpCas9: NGG (3')), SpCas9-NG (SpCas9-NG: NG (3')), SpG (SpG: NGN (3')), SpRY (SpRY: NRN (3')), xCas9 (xCas9: NG (3')), SaCas9 (SaCas9: NNGRRT (3')), SaCas9-KKH (SaCas9-KKH: NNNRRT (3')), AsCas12a (AsCas12a: TTTV (5')), LbCas12a (LbCas12a: TTTV (5')), enAsCas12a (enAsCas12a: TTTV (5')).	SpCas9
`region_end`	No	restrict results to guides ending at/before this position. In bp. Advanced.
`region_start`	No	restrict results to guides starting at/after this position (0-based). In bp. Advanced.
`restriction_enzymes`	No	cloning enzymes whose recognition site must NOT appear in the spacer. Advanced.

Output Schema

Name	Required	Description
`count`	Yes	guides passing the region filter
`guides`	Yes	the designed guides, scored
`region`	Yes	the window the guides were filtered to, resolved: start, end, and whether it is the whole molecule. Reported because `region_start`/`region_end` are optional and their default is the molecule's length, which a caller holding only this result does not have — without it, `count` of `totalCandidates` cannot be read
`topSpacer`	Yes	spacer of the highest-ranked guide
`totalCandidates`	Yes	candidates found before filtering

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 23, 2026

addedOutput schema / properties / region

Added value: +{
+  "description": "the window the guides were filtered to, resolved: start, end, and whether it is the whole molecule. Reported because `region_start`/`region_end` are optional and their default is the molecule's length, which a caller holding only this result does not have — without it, `count` of `totalCandidates` cannot be read"
+}

changedOutput schema / required

Previous value: -[
-  "guides",
-  "count",
-  "totalCandidates",
-  "topSpacer"
-]New value: +[
+  "guides",
+  "count",
+  "totalCandidates",
+  "topSpacer",
+  "region"
+]

First observedOct 20, 2026

TDQS

B3.2/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false, openWorldHint=false, so the safety profile is covered. The description adds useful substance by enumerating the analysis it performs (on/off-target scoring, QC flags, cloning-enzyme conflict detection), but says nothing about scoring method, reference requirements for off-target search, or computational cost.

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?

Two compact sentences with the outputs front-loaded after the verb; no filler. The trailing 'Nuclease list comes from the real nuclease registry' is the weakest part — more promotional than informative — but it is brief.

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 a fully documented 7-parameter schema, an output schema, and explicit annotations, the description only needs to convey intent and scope, which it does. The main gap is whether off-target scoring requires an external reference or is intrinsic, which an agent about to run the tool would want to know.

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%, so the baseline is 3. The description only adds the note that nuclease choices come from a 'real nuclease registry' — mildly informative but not needed, since the enum already lists each nuclease with its PAM. It says nothing extra about min_stem, region bounds, or restriction_enzymes.

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 pair (design and score) and resource (CRISPR guides) plus the concrete outputs: on/off-target scores, QC flags, cloning-enzyme conflicts. This distinguishes it implicitly from siblings like crispr_design_library, screen_guides, and crispr_score_deephf, 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 Guidelines2/5

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

There is no guidance on when to reach for this tool versus screen_guides, crispr_design_library, search_off_targets, or fold_guide, and no stated prerequisites or exclusions. The phrase 'on the subject' hints at the input shape but is not usage guidance.

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?