Skip to main content
Glama

align_pair

Read-only

Align TWO sequences on their own, globally (Needleman-Wunsch, or Gotoh with an affine penalty) or locally (Smith-Waterman / Gotoh), through biotite's align_optimal with the MSA panel's own knobs: substitution matrix, linear or affine gaps, and for a global alignment whether end gaps are charged.

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": {
      "sequences": "<sequences>"
    },
    "name": "align_pair"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNo`global` aligns the two end to end; `local` finds the best-scoring stretch shared by both. Values: global (Global (Needleman-Wunsch / Gotoh)), local (Local (Smith-Waterman / Gotoh)).global
_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.
gap_openNoaffine only: the penalty for starting a gap. Negative. Only applies when affine_gap is true.
sequencesYesexactly two sequences: wire two upstream outputs here, or name two library documents.
affine_gapNo`true` charges separate opening and extension penalties (Gotoh); `false` one flat penalty per gap column.
gap_extendNoaffine only: the penalty for each column a gap is extended by. Negative. Only applies when affine_gap is true.
gap_penaltyNothe flat penalty per gap column. Negative. Only applies when affine_gap is false.
align_matrixNothe substitution matrix. `auto` reads the alphabet: EDNAFULL for nucleotides, BLOSUM62 for protein. Values: auto (Auto - from the alphabet), EDNAFULL (EDNAFULL - nucleotides (EMBOSS NUC.4.4)), BLOSUM62 (BLOSUM62 - amino acids).auto
terminal_penaltyNoglobal only: `true` charges overhanging ends like an internal gap; `false` makes them free. Only applies when mode is global.

Output Schema

NameRequiredDescriptionDefault
scoreYesthe alignment score under the matrix and gap penalties
spansYes1-based first and last residue of each input inside the aligned stretch
summaryYesthe method, the score and where the aligned stretch lies in each input
alignedSequencesYesthe two aligned rows, {name, aligned}, over the aligned stretch

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, openWorldHint=false and destructiveHint=false, so the safety profile is covered; the description adds that the operation delegates to biotite's `align_optimal` and enumerates which knobs are honored (matrix, linear vs affine gaps, terminal gaps). It does not mention input limits, alphabet restrictions, or how ties/overhangs are reported, but an output schema exists to carry return details.

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 dense sentence front-loads the core action and scope, then enumerates the adjustable knobs with no filler. It is somewhat long and punctuation-heavy, but every clause carries information about the alignment behavior.

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 10-parameter tool with a 100%-covered schema, full annotations and an output schema, the description supplies the algorithmic context an agent needs to pick a mode and gap model. Minor gaps (no statement that `sequences` must contain exactly two strings beyond the word "TWO", no tie-breaking or length-limit notes) are already handled 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 coverage is 100%, so the parameter baseline is 3; the description's list of knobs (substitution matrix, linear or affine gaps, end-gap charging) largely restates what the schema already documents. It adds modest conceptual framing (affine = Gotoh, terminal penalty = whether end gaps are charged) but no format, sign, or interaction details beyond the schema.

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?

The description names a specific verb and resource ("Align TWO sequences on their own") and pins down the algorithms used (Needleman-Wunsch / Gotoh / Smith-Waterman) via biotite's `align_optimal`. The emphasis on "TWO sequences" and the pairwise scope distinguishes it from the multi-sequence sibling `align_sequences` without needing to open either schema.

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

Usage Guidelines4/5

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

It clearly frames the pairwise case and contrasts the two modes (global end-to-end vs local best-scoring stretch), which tells an agent when each mode applies. However, it never explicitly names an alternative sibling (e.g. when to prefer `align_sequences` or `ebi_align`) or states exclusions, so routing is inferred rather than instructed.

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