Skip to main content
Glama

hmmscan

Read-only

Which of MANY profile HMMs does this protein carry? Runs HMMER 3.4's hmmscan pipeline on this machine: the MSV, bias, Viterbi and Forward filters per model, domain definition by posterior decoding (several domains of one model are split, as hmmscan splits them), null2-corrected domain scores, and hmmscan's reporting thresholds.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "hmmscan"
  }
}

Input Schema

NameRequiredDescriptionDefault
ENohmmscan -E: report models with an E-value at or below this.
F1Nohmmscan --F1: the MSV filter’s P-value threshold. Advanced.
F2Nohmmscan --F2: the Viterbi filter’s P-value threshold. Advanced.
F3Nohmmscan --F3: the Forward filter’s P-value threshold. Advanced.
domENohmmscan --domE: report domains with a conditional E-value at or below this.
pfamNoPfam accessions to fetch from InterPro and add to the database, comma-separated (PF00069,PF00017).
_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.
proteinNothe query protein, one-letter codes. Empty takes the open record when it is a protein.
_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.
alphabetNowhat the query is. `auto` reads them the way HMMER does (Easel’s composition rule). Set it when a short or unusual set is read wrongly: every DNA base is also an amino-acid letter, so a nucleotide set against a protein model scores without complaint and means nothing. Values: auto (Auto (Easel’s rule)), protein (Protein), nucleotide (Nucleotide). Advanced.auto
profilesNo`.hmm` files to scan against, by name, from the project or the `_files` sent with the call; each may hold many models. Empty takes every `.hmm` there.

Output Schema

NameRequiredDescriptionDefault
ZYesmodels scanned, which every E-value is scaled by
hitsYesevery model that passed the pipeline, best first: model, accession, bits, evalue, reported, aboveGathering, and its domains (envFrom/envTo, aliFrom/aliTo on the query, hmmFrom/hmmTo, bits, iEvalue, cEvalue, reported, aboveGathering)
domainsYesthe reported domains alone, in query order, each with its model name: the domain architecture
reportedYesmodels reported

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.6/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so safety is covered; the description goes further by disclosing that computation happens locally on this machine and by enumerating the pipeline stages (MSV, bias, Viterbi, Forward filters, posterior-decoding domain definition, null2 correction, reporting thresholds). That is substantive algorithmic disclosure beyond the annotations, though it omits cost/runtime expectations for a possibly large HMM library.

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?

One dense but well-ordered sentence: the guiding question is front-loaded, then the pipeline is enumerated in execution order. Every clause carries information, though the parenthetical about domain splitting is slightly labored and the whole is a single unbroken sentence.

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?

The tool is complex — 11 parameters, nested _subject/_files objects, an output schema — and the description covers the algorithm and locality well while the schema covers parameters and the output schema covers returns. What is missing is decision-level context: when to choose hmmscan over a single-model or single-sequence search, and what database state the scan assumes.

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% and the schema already spells out every flag (E, domE, F1/F2/F3, pfam, profiles, alphabet) including HMMER flag names. The description adds no parameter-level meaning beyond the schema, so the baseline of 3 applies — no deficit, no bonus.

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 opening question — 'Which of MANY profile HMMs does this protein carry?' — plus 'Runs HMMER 3.4's hmmscan pipeline on this machine' names both the resource (profile HMM database) and the operation (many-model scan against one query). The 'MANY profile HMMs' framing implicitly separates it from a single-model search, but no sibling tool is named, so the differentiation is left to inference.

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 only implied by the framing question; there is no explicit 'use this when…' clause, no statement of prerequisites (a populated .hmm library), and no named alternative for the single-model or single-sequence case. An agent can infer it is the many-model scan, but must fall back on the schema to learn that empty inputs default to the open record and every .hmm in the project.

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