Skip to main content
Glama
Sign In

Jean — Molecular Biology & Genomics

by io.github.genmnz
OverviewDiscussionsAdmin

crispr_score_deephf

Read-only

Score CRISPR guides with DeepHF: a predicted knockout EFFICIENCY between 0 and 1 for wild-type SpCas9 (U6 or T7 promoter), eSpCas9(1.1) or SpCas9-HF1.

Input Schema

NameRequiredDescriptionDefault
modelNowhich published model to score under. This is a scientific choice about YOUR experiment — which Cas9 variant, and which promoter the sgRNA is expressed from — not a quality setting, and scores from two models are not comparable. Values: wt_u6 (WT SpCas9 · U6 promoter), wt_t7 (WT SpCas9 · T7 promoter), wt (WT SpCas9 · both promoters), esp (eSpCas9(1.1)), hf (SpCas9-HF1).wt_u6
_filesNoThe 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.
_subjectNoThe 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.
protospacersYesthe 23-nt protospacers to score — 20-nt spacer plus the 3-nt PAM, exactly as DeepHF takes them. Anything that is not 23 nt of unambiguous A/C/G/T ending in GG scores null rather than being silently trimmed or extrapolated.

Output Schema

NameRequiredDescriptionDefault
bestYesthe highest-scoring protospacer, or empty when none could be scored
modelYeswhich model produced these numbers. Scores from two models are not comparable
scoredYeshow many of the inputs DeepHF is defined on — the accounting, not an assumption
scoresYesevery protospacer with its efficiency, IN THE ORDER GIVEN — null where DeepHF is not defined, with the reason beside it
efficienciesYesjust the numbers, same order — null-preserving, so it lines up with the input

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

B3.3/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is fully covered. The description adds the output type and 0-1 range, but with an output schema present that is largely redundant, and it says nothing about runtime, batch limits, or what happens with invalid inputs (the schema's null-scoring rule carries that).

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?

A single front-loaded sentence led by the verb, with no filler or repetition. Parenthetical variant and promoter details are compact and earn their space.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Annotations, output schema, and full schema coverage carry most of the burden, and the description supplies the essential output interpretation. What is missing is the sibling boundary — for a scoring tool where results from different models are not comparable, failing to route between deephf and deepspcas9 is a real completeness gap.

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 coverage is 100%, so the model enum, the 23-nt protospacer requirement, and the _subject/_files record are all fully documented in structured fields. The description only restates the variant list at a coarser grain than the enum does, adding no syntax or format detail beyond the schema.

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+resource (score CRISPR guides), names the underlying model (DeepHF), and states the output semantics ('predicted knockout EFFICIENCY between 0 and 1') plus the supported Cas9 variants. It never distinguishes itself from the near-identical sibling crispr_score_deepspcas9, so an agent must open both schemas to tell which scorer applies.

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?

No when-to-use, when-not-to-use, or alternative routing is stated. The listed variants hint at selection criteria, but nothing tells an agent to prefer this over crispr_score_deepspcas9, screen_guides, or crispr_design_guides, and the crucial warning that scores are model-specific lives only in the schema.

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

All Jean — Molecular Biology & Genomics 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