Skip to main content
Glama

blast_sequence

Read-onlyIdempotent

BLAST a DNA or protein sequence (raw or FASTA; up to 20 kb DNA or 5,000 aa) against this site's databases: pea, narrow-leafed lupin, faba bean, soybean, common bean, chickpea and lentil genomes, CDS and proteins. The program is chosen from the query and database types (blastn, or blastn-short under 50 nt; blastx; blastp; tblastn against CDS only). databases: ids from the list this tool returns (default: DNA query -> reference genome + all CDS sets; protein -> all protein sets). Hits give gene ID (CDS/protein) or genome position with overlapping genes, identity, alignment length, e-value and a genome browser link. People can use the SequenceServer page at /blast/ for the same databases.

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": {
      "sequence": "<sequence>"
    },
    "name": "blast_sequence"
  }
}

Input Schema

NameRequiredDescriptionDefault
evalueNo
max_hitsNo
sequenceYes
databasesNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / databases / anyOf
      Previous value: -[
      -  {
      -    "items": {
      -      "type": "string"
      -    },
      -    "type": "array"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]New value: +[
      +  {
      +    "items": {
      +      "type": "string"
      +    },
      +    "type": "array"
      +  },
      +  {
      +    "type": "string"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
  2. Added

TDQS

A4.4/5.0
Behavior5/5

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

Goes well beyond the readOnly/openWorld/idempotent annotations by disclosing input size ceilings (20 kb DNA, 5,000 aa), the automatic program-selection rules, the tblastn/CDS restriction, and exactly what a hit contains (gene ID or genome position with overlapping genes, identity, alignment length, e-value, browser link). Those constraints are what an agent needs to avoid malformed calls.

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?

Front-loads the action and input type, then layers database scope, program selection, defaults, and output shape in a compact, information-dense form. The trailing note about the SequenceServer page is the only near-extraneous sentence, and it is short.

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?

With no output schema, the description usefully characterizes the return shape and adds size limits and program logic, so an agent can call it confidently. The gap is the unexplained evalue and max_hits parameters, which leaves hit-count control underspecified for a 4-parameter tool.

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 0%, so the description must carry all four parameters; it covers sequence (raw/FASTA with length caps) and databases (IDs from a list, with per-query-type defaults) well, but says nothing about evalue or max_hits, which remain undocumented anywhere. Partial compensation for the coverage gap warrants a 3 rather than a 4.

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?

States a specific verb (BLAST) and resource (DNA or protein sequence raw or FASTA) against a named set of legume genome/CDS/protein databases. This is unmistakably a sequence-similarity search and clearly distinct from the gene, literature, and annotation siblings.

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?

Explains the conditions that select each program (blastn, blastn-short under 50 nt, blastx, blastp, tblastn against CDS only) and what the databases default to for DNA vs protein queries, plus the /blast/ web page as a human alternative. It lacks an explicit 'use this instead of find_gene / legume_gene when you have a raw sequence' framing, so it stops short of full when/when-not guidance.

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