Skip to main content
Glama

alignment_window

Read-only

Read one window of a BAM or SAM in this project: its reads, the depth across it, and what the pairs say about the library — the same window, filters and record cap the pileup draws. Wire reads into an alignment or a screen the way the pane's own hand-offs do.

Input Schema

NameRequiredDescriptionDefault
locusNothe window, as a locus string (`ctgA:1-50,001`). Unset, it is the whole of the alignment's first reference — the window the panel opens on.
_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.
min_mapqNohide reads below this mapping quality, as the pane’s Filter reads operation does. The reads are still counted — `hidden` says how many this removed.
alignmentNowhich BAM or SAM in this project, by name. Unset, it is the project's only alignment — and it refuses rather than guessing when there is more than one.
max_readsNothe record cap. More reads than this overlap the window and the result is an even SAMPLE of them, with `sampled` saying so — the pane’s own cap is the default.
hide_secondaryNodrop secondary alignments (FLAG 0x100).
hide_duplicatesNodrop reads marked as PCR or optical duplicates (FLAG 0x400).
hide_supplementaryNodrop supplementary alignments (FLAG 0x800).

Output Schema

NameRequiredDescriptionDefault
readsYesthe reads in the window after filters: name, reference, 1-based start and end, strand, MAPQ, CIGAR, TLEN and sequence — the shape an alignment or a screen takes
hiddenYesreads in the window the filters removed — 0 with an active filter is a real answer
windowYesthe window actually read, as a locus string
sampledYesmore reads overlap the window than the cap allows, so `reads` is an even sample rather than all of them
coverageYesthe depth profile as bins across the window, in order
depthPlotYesthe coverage track as the pileup draws it: each bin's lowest, mean and highest per-base depth over ALL reads, so a dropout narrower than a bin still shows in the minimum
depth_maxYesthe deepest bin
depth_meanYesmean depth across the window’s coverage bins, over ALL reads — the coverage track is full-depth, as BamView’s is, so filters do not move it
read_countYeshow many reads that is
insert_sizeYesthe |TLEN| band this library’s own proper pairs define — `min`, `max` and whether it was MEASURED here or is the untuned fallback, which is what decides whether an insert is abnormal

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedOutput schema / properties / depthPlot
      Added value: +{
      +  "description": "the coverage track as the pileup draws it: each bin's lowest, mean and highest per-base depth over ALL reads, so a dropout narrower than a bin still shows in the minimum",
      +  "properties": {
      +    "mark": {
      +      "enum": [
      +        "line",
      +        "bar",
      +        "point"
      +      ],
      +      "type": "string"
      +    },
      +    "rules": {
      +      "items": {
      +        "properties": {
      +          "label": {
      +            "type": "string"
      +          },
      +          "y": {
      +            "type": "number"
      +          }
      +        },
      +        "required": [
      +          "y",
      +          "label"
      +        ],
      +        "type": "object"
      +      },
      +      "type": "array"
      +    },
      +    "series": {
      +      "items": {
      +        "properties": {
      +          "name": {
      +            "type": "string"
      +          },
      +          "y": {
      +            "items": {
      +              "type": [
      +                "number",
      +                "null"
      +              ]
      +            },
      +            "type": "array"
      +          }
      +        },
      +        "required": [
      +          "name",
      +          "y"
      +        ],
      +        "type": "object"
      +      },
      +      "type": "array"
      +    },
      +    "title": {
      +      "type": "string"
      +    },
      +    "x": {
      +      "items": {
      +        "type": "number"
      +      },
      +      "type": "array"
      +    },
      +    "xLabel": {
      +      "type": "string"
      +    },
      +    "yLabel": {
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "x",
      +    "series",
      +    "xLabel",
      +    "yLabel"
      +  ],
      +  "type": [
      +    "object",
      +    "null"
      +  ]
      +}
    • changedOutput schema / required
      Previous value: -[
      -  "reads",
      -  "read_count",
      -  "hidden",
      -  "sampled",
      -  "window",
      -  "depth_mean",
      -  "depth_max",
      -  "coverage",
      -  "insert_size"
      -]New value: +[
      +  "reads",
      +  "read_count",
      +  "hidden",
      +  "sampled",
      +  "window",
      +  "depth_mean",
      +  "depth_max",
      +  "coverage",
      +  "depthPlot",
      +  "insert_size"
      +]
  2. First observed

TDQS

A3.5/5.0
Behavior3/5

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

Annotations already declare this as a safe, read-only, non-destructive, non-open-world operation. The description adds useful context that the window, filters, and record cap match the pileup, and mentions downstream hand-offs, but it does not surface refusal conditions or sampling behavior in the description itself — those live only in the schema.

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 sentences, front-loaded with the purpose, with no obvious filler. The second sentence uses somewhat opaque jargon ('hand-offs') but remains 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?

For a complex read-only tool with nine parameters, full schema coverage, and an output schema, the description is reasonably complete: it identifies the resource, the returned data categories, and the pileup-consistency behavior. The main missing pieces, such as refusal when multiple alignments exist and filtering/sampling semantics, are covered by the schema.

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 all nine parameters are already documented in detail. The tool description only alludes generally to window, filters, and record cap; it does not add parameter meaning beyond what the schema provides.

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 clearly states a specific verb and resource: read one window of a BAM or SAM, returning reads, depth, and pair/library information. It is understandable without opening the schema, though it does not explicitly distinguish itself from nearby alignment-related siblings such as map_reads or browse_region.

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?

Usage is implied by the window/pileup framing and the hand-off note about wiring `reads` into an alignment or screen. However, no explicit when-to-use, when-not-to-use, or named alternative tools are provided, so the agent must infer appropriate contexts.

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