verify_construct
Compare a sequencing RESULT against the construct you designed and say what differs, where, and what it lands in.
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": {
"design": "<design>",
"result": "<result>"
},
"name": "verify_construct"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| match | No | alignment limit `match`, as the Verify panel's own slider sets it. Advanced. | |
| _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. | |
| design | Yes | the construct you INTENDED — wire an upstream record or name a library document. Its features come with it, and they are what turns a difference into a consequence. | |
| result | Yes | what actually came back from sequencing — wire a record or name a document. | |
| _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. | |
| gap_open | No | alignment limit `gapOpen`, as the Verify panel's own slider sets it. Advanced. | |
| mismatch | No | alignment limit `mismatch`, as the Verify panel's own slider sets it. Advanced. | |
| word_size | No | alignment limit `wordSize`, as the Verify panel's own slider sets it. Advanced. | |
| gap_extend | No | alignment limit `gapExtend`, as the Verify panel's own slider sets it. Advanced. | |
| band_margin | No | alignment limit `bandMargin`, as the Verify panel's own slider sets it. Advanced. | |
| min_coverage | No | alignment limit `minCoverage`, as the Verify panel's own slider sets it. Advanced. | |
| confident_coverage | No | alignment limit `confidentCoverage`, as the Verify panel's own slider sets it. Advanced. | |
| min_result_fraction | No | alignment limit `minResultFraction`, as the Verify panel's own slider sets it. Advanced. |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| report | Yes | the whole verification, including the alignment frame and band | |
| identity | Yes | positions where design and result agree, over the aligned length, as a PERCENTAGE — 100 for an exact match, not 1 | |
| differences | Yes | every difference with its 1-based position on the design and a one-line description | |
| largeEvents | Yes | structural events — a dropped cassette or a duplicated span reads as one event here rather than as hundreds of substitutions | |
| differenceCount | Yes | substitutions, insertions and deletions found — NOT counting positions the sequencer could not call | |
| affectedFeatures | Yes | features with a real difference, missing bases or uncalled positions — worst first | |
| worstConsequence | Yes | the most severe consequence term any affected feature carries, by Ensembl's published ranking — the one value a gate should read | |
| uncalledPositions | Yes | positions the result could not call. Counted apart from differences on purpose: an uncalled base is not a mutation, and folding the two together reports a clean read as a damaged one |