Skip to main content
Glama
mitomap-link
by berntpopp

Get MITOMAP Variant

get_variant
Read-onlyIdempotent

Look up a single mtDNA allele on the rCRS reference in MITOMAP to retrieve its locus, disease status, plasmy, GenBank frequency, and PMIDs; unlisted alleles return found=false.

Instructions

Look up one mtDNA allele in MITOMAP on the rCRS reference (NC_012920.1): every MITOMAP record for it (coding/control-region or rRNA/tRNA disease mutation, polymorphism) with locus, disease, MITOMAP status verbatim ('Reported', 'Cfrm' = confirmed; a bracketed ClinGen VCEP rating is split out), homoplasmy/heteroplasmy as reported, GenBank count/frequency and PMIDs. Accepts m.3243A>G, NC_012920.1:m.3243A>G, MT-3243-A-G, chrM:3243 A>G, A3243G, and HGVS indels (m.5133_5134del, exact MITOMAP allele match). Other mito references (Yoruba NC_001807, RSRS) and rCRS reference-base mismatches are rejected. An allele MITOMAP does not list returns found=false, not an error. Signature: get_variant(variant, response_mode=).

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": {
      "variant": "<variant>"
    },
    "name": "get_variant"
  }
}

Input Schema

NameRequiredDescriptionDefault
variantYesmtDNA variant on rCRS, e.g. m.3243A>G, MT-3243-A-G, chrM:8344 A>G or m.5133_5134del.
response_modeNoVerbosity: minimal (ids, locus, disease, status) | compact (default; + alleles, plasmy, GenBank counts, reference_count) | standard (get_variant: + up to 10 references with fenced titles; search_variants: + up to 10 PMIDs) | full (get_variant: + up to 50 references and every PMID; search_variants: + every PMID).compact

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.3

TDQS

A4.5/5.0
Behavior5/5

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

Goes well beyond the annotations (readOnly/idempotent/openWorld) by disclosing input normalization rules, the exact rejection conditions for wrong references and mismatched reference bases, the semantics of verbatim MITOMAP status values including the ClinGen VCEP rating split, and the explicit 'found=false, not an error' contract. These are the behaviors an agent actually needs to interpret results and handle misses.

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?

Purpose is front-loaded in the first clause, followed by return contents, accepted formats, exclusions, and the not-found contract — a logical order with no filler sentences. It is dense to the point of being a single run-on, and format examples partly duplicate the schema examples, which keeps it just below the top mark.

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 two-parameter read-only lookup with no output schema, the description covers operation, accepted inputs, rejection rules, returned fields, status semantics, and the empty-result contract — enough to call and interpret it correctly. Only minor operational details (e.g., any rate limits or whether reference lists are truncated at the default mode) are left unstated.

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?

Schema coverage is already 100%, so the baseline is 3, but the description adds real meaning: concrete accepted spellings (m.3243A>G, NC_012920.1:m.3243A>G, MT-3243-A-G, chrM:3243 A>G, A3243G) and the constraint that HGVS indels must be an exact MITOMAP allele match. response_mode is not elaborated in prose, but the schema enum already documents it fully.

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 and resource ('Look up one mtDNA allele in MITOMAP on the rCRS reference'), scoped to a single allele, which cleanly separates it from search_variants. It also enumerates exactly what a record contains (locus, disease, status, plasmy, GenBank counts, PMIDs), so an agent knows both the operation and its output shape without opening anything else.

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?

Gives clear conditions for use: one allele, on rCRS, with a long list of accepted input notations and explicit exclusions (Yoruba NC_001807, RSRS, rCRS reference-base mismatches). It also clarifies the not-found case ('returns found=false, not an error'). It stops short of naming search_variants as the alternative for multi-variant or fuzzy queries, so routing guidance is implied rather than explicit.

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