Skip to main content
Glama
berntpopp
by berntpopp

Get Variant Counts

get_variant_counts
Read-onlyIdempotent

Retrieve per-position variant counts from gnomAD and/or ClinVar for a human transcript, filtered by source and position range.

Instructions

Return per-position gnomAD and/or ClinVar variant counts on a built landscape, filtered by source (both|gnomad|clinvar). Accepts a single position, a [position_start, position_stop] range, or the whole protein (paginated); when source includes clinvar each residue's ClinVar variants are listed with NCBI urls. Signature: get_variant_counts(transcript_id=, position=, position_start=, position_stop=, source=, limit=, offset=, response_mode=).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNoMaximum rows to return (1..1000; default 200).
offsetNoZero-based offset into the result list (for paging).
sourceNoVariant source to report: both|gnomad|clinvar (default both).both
positionNoA single 1-based residue position.
position_stopNoInclusive stop of a residue range.
response_modeNoVerbosity: minimal|compact|standard|full (default compact).compact
transcript_idYesA versioned Ensembl transcript id (the .N version suffix is required), e.g. ENST00000269305.4. Resolve a gene symbol with resolve_transcript first.
position_startNoInclusive start of a residue range.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
hintNo
_metaNo
fieldNo
totalNo
sourceNo
messageNo
successYes
returnedNo
positionsNo
retryableNo
candidatesNo
error_codeNo
paginationNo
data_versionsNo
transcript_idNo
recovery_actionNo
recommended_citationNo
Behavior4/5

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

Annotations already declare the tool as read-only, idempotent, and non-destructive. The description adds useful behavioral details: it accepts pagination (limit/offset), returns ClinVar variants with NCBI URLs, and works on a built landscape. No contradictions.

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?

The description is concise (two sentences plus a signature line), front-loaded with the primary purpose, and includes all key details without redundancy.

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?

Given 8 parameters and an output schema, the description covers the essential usage (position input, source filtering, pagination). It omits details on response_mode but that's in the schema. The tool complexity is well addressed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema covers all parameters (100% coverage), but the description adds meaning by explaining how position inputs work (single, range, whole protein) and the signature. This helps the agent understand the parameter semantics 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 clearly specifies the tool returns per-position variant counts from gnomAD and/or ClinVar on a built landscape, with filtering by source and flexible position input (single, range, whole protein). It distinguishes from sibling tools like 'get_position_tolerance' and 'get_tolerance_landscape' by focusing on variant counts.

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?

The description provides clear context on when to use the tool (for variant counts by position/source) and mentions pagination. However, it does not explicitly state when not to use it or suggest alternatives, but the sibling list implies other tools for different purposes.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/berntpopp/metadome-link'

If you have feedback or need assistance with the MCP directory API, please join our Discord server