Skip to main content
Glama

CRISPR guide off-target check

crispr_offtarget_check
Read-onlyIdempotent

Screen a guide's protospacer for off-target sites (protospacer match + valid PAM, both strands) against a small curated set of common lab reference genomes (see genomesChecked) — NOT a whole human/mouse genome search. For SpCas9 with a 20 nt spacer each site also gets a Doench 2016 CFD score, so sites are ranked by predicted cut likelihood rather than by mismatch count alone, and the guide gets an aggregate specificity. Use this the same way primer_specificity is used: a useful sanity check within the covered organisms, not a clearance guarantee for a mammalian expression host. PREDICTED, NOT MEASURED. Best of the common off-target scores on the authors' GUIDE-Seq comparison, at Pearson r = 0.40 over 9 guides and 402 sites (vs CCTop 0.31, Hsu-Zhang 0.26) — a useful ranking, not a reliable magnitude. Weights were measured for SINGLE mismatches; multiple mismatches are multiplied, and Listgarten et al. 2018 note the training data never contained a mismatch and an alternative PAM together, so that combination is extrapolation. Valid for: SpCas9 with a 20 nt spacer, which is the only case scored — every other nuclease returns null rather than a number from the wrong enzyme's table. One locus, one cell line. Substitutions only: DNA/RNA bulges are neither searched nor scorable, and a low score is not a claim that a site is safe.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nucleaseNoNuclease id — determines the PAM pattern/side required at each candidate site.spcas9
protospacerYesThe guide's protospacer sequence, 5'→3' (no PAM). Max 32 nt — every supported nuclease uses a 20–23 nt guide.
maxMismatchesNoMismatches tolerated between the protospacer and a candidate genomic site. Max 4 — a complete search seeds on maxMismatches+1 non-overlapping blocks, and past that the blocks are too short to be selective against a multi-Mb genome (a site that mismatched more would not be cut anyway).

TDQS

A4.7/5.0
Behavior5/5

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

Annotations already provide readOnlyHint, openWorldHint, and idempotentHint. Description adds extensive behavioral detail: CFD scoring only for SpCas9 20nt spacer, Pearson correlation 0.40, single mismatch limitation, null returns for unsupported nucleases, and that DNA/RNA bulges are not searched. No contradictions with annotations.

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?

The description is front-loaded with the core purpose and then adds important caveats. It could be slightly more concise (e.g., the GUIDE-Seq comparison detail is valuable but adds length), but each sentence earns its place for capturing nuanced behavior. No waste.

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 tool's complexity (3 parameters, no output schema, nuanced behavioral constraints), the description covers purpose, scope, limitations, scoring validity, and exception cases. Without output schema, describing the ranking output would improve completeness, but the description is already thorough for a read-only computation tool.

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 description coverage is 100%, so baseline is 3. Description adds value by explaining the broader context: that maxMismatches seeding uses maxMismatches+1 blocks, and that nuclease determines PAM pattern. However, it doesn't explicitly describe the allowed sequence range for protospacer beyond what schema provides.

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?

Description clearly states the tool screens a protospacer for off-target sites (protospacer match + valid PAM, both strands) against curated lab reference genomes, not whole genomes. This distinctively positions it from sibling tools like crispr_grna_design or primer_specificity, with explicit scope limitations.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

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

Explicitly says to use 'the same way primer_specificity is used: a useful sanity check within the covered organisms, not a clearance guarantee.' States what it's NOT (whole genome search, measured data, safe for multiple mismatches + PAM combinations, valid for non-SpCas9 nucleases). Provides clear when-to-use and when-not-to-use guidance.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.6/5.0
Disambiguation4/5

Most tools have highly specific purposes (e.g., crispr_grna_design vs base_editing_design vs prime_editing_design). However, there is some overlap in sequence analysis tools (characterize_sequence, sequence_report) and plasmid annotation tools (plasmid_annotate vs plasmid_deep_annotate) which could cause confusion.

Naming Consistency3/5

The naming pattern is largely consistent with snake_case verb_noun or noun_descriptor (e.g., primer_design, plasmid_annotate, fastq_trim). However, there are exceptions like 'batch', 'workflow', 'gc_content', and 'cloning_diagnose' which don't follow the verb_noun pattern consistently. Also, some names are phrases like 'golden_gate_from_parts'.

Tool Count2/5

With 101 tools, this server is extremely large and likely overwhelming for agents. Even for a comprehensive bioinformatics toolkit, this exceeds a manageable scope, risking agent confusion and inefficient tool selection. A more modular approach would be advisable.

Completeness4/5

The tool surface covers a wide range of bioinformatics workflows including sequence analysis, primer design, cloning, CRISPR, NGS, expression analysis, and data export. There are minor gaps such as lack of a dedicated protein structure prediction tool and limited off-target genome coverage, but overall the set is impressively complete for its domain.

Resources