Skip to main content
Glama

quantify_base_editing

Read-only

Quantify BASE EDITING from a single Sanger trace, with no control read — the EditR method (Kluesner et al. 2018), graded against the authors' own R.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "guide": "<guide>"
    },
    "name": "quantify_base_editing"
  }
}

Input Schema

NameRequiredDescriptionDefault
guideYesthe protospacer, 5'→3', without the PAM. Matched exactly against the read's own base calls; the coordinates it lands on come back in the result.
trim3Nolast base of the read the background model may be fitted on, 1-based inclusive. Pair it with `trim5`.
trim5Nofirst base of the read the background model may be fitted on, 1-based inclusive. GIVE BOTH BOUNDS OR NEITHER — upstream errors on a lone one rather than filling the other in. Left unset, upstream's automatic rule runs: drop the first 20 bases, then drop every base whose total peak height is under a tenth of the mean of what is left. The window is an INPUT to the answer, not a view: it is what the noise is estimated from, so tightening it lowers the cut-off.
_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.
documentNowhich trace file to read: its name (`read_F.ab1`) or its project file id. LEAVE IT EMPTY to run on the chromatogram tab that is open. A file id is project-specific, so a template ships this unset.
guide_endNothe other end of an explicit placement, 1-based inclusive. Pair it with `guide_start`.
guide_startNoplace the guide yourself, 1-based inclusive in the read's own base calls, instead of matching it exactly. GIVE BOTH BOUNDS OR NEITHER. This is what a read carrying a sequencing error inside the protospacer needs: the analysis tests the bases you point at rather than refusing the read.
p_value_cutoffNoa base is called as edited when its share of the position's signal clears this trace's own noise model at this probability. EditR's own default is 0.01.
guide_is_reverse_complementNosearch for the guide's reverse complement. A C→T edit on the guide strand then reads as G→A in the result.

Output Schema

NameRequiredDescriptionDefault
callsYesevery significant call: { guidePosition, index, guideBase, base, percent, pValue }, biggest first
editedYeswhether ANY base of the guide carries a non-reference signal above this trace's own noise. Wire it into a gate
reportYesthe whole run: every guide position with all four base percentages and p-values, the four fitted noise models and their cut-off lines. This is what makes a negative checkable — 'no editing' and 'the model could never have fired' look identical without it
topChangeYesthe biggest call as `reference→edited`, e.g. `C→T`. Empty when there is none
guideStartYes1-based position in the read's own base calls where the guide was found — what a canvas needs to draw it
topPercentYesits share of that position's total peak height, 0–100
topPositionYesthe guide position (1-based) of the biggest call, or 0 when there is none

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

B3.4/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false and a closed-world scope, so safety is covered. The description adds genuine behavioral value by disclosing the underlying method and that it was validated against the authors' R implementation, which signals expected fidelity. It stops short of describing runtime characteristics like how large a trace it accepts or what it does with an ambiguous read.

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?

A single front-loaded sentence with the key constraint (single trace, no control) stated first, followed by method provenance. Nothing is wasted, though 'graded against the authors' own R' is terse enough to be slightly opaque without context.

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?

An output schema exists, so return values need no explanation, and the parameters are fully documented in the schema. However, for a ten-parameter quantitative analysis with nested record objects, the description gives no hint of the analysis outputs (edit percentages, calls) or of prerequisites like trace file format, leaving moderate gaps.

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 every one of the ten parameters already carries rich documentation, including the trim-window tradeoff and guide placement behavior. The description itself contributes no additional parameter guidance, which is the expected baseline-3 outcome when the schema does the work.

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 names a specific verb+resource (quantify base editing) and pins the input modality precisely: a single Sanger trace with no control read. That 'no control read' clause implicitly separates it from paired-sample quantifiers, but it never names a sibling explicitly, so an agent must infer the boundary.

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?

The single-trace/no-control framing implies when this tool applies, and the method attribution (EditR) helps an agent recognize the scenario. There is no explicit when-not guidance or named alternative such as a control-paired editing quantifier, so routing is left partly to inference.

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.

Resources