Skip to main content
Glama

Immunology Search

immunology_search
Read-onlyIdempotent

Search the LANL HIV Molecular Immunology Database for T-cell epitopes (CTL/CD8+ or T-helper/CD4+) or antibody binding sites, a different question from catnap_search_neutralization: this is about WHERE on the virus an immune response targets and WHICH HLA restricts it, not how potently an antibody neutralizes. Answers "what CTL epitopes are in HIV Gag", "which antibodies bind the CD4 binding site", "what HLA restricts this epitope", "find epitopes at position 296-331 of Env". Queried LIVE against LANL's own keyless JSON API (no ingest, always current). table selects which of the three response types you get: ctl (CD8+ T-cell), helper (CD4+ T-cell), or ab (antibody binding sites). At least one of mab_name, epitope, protein_name is required. Returns citation, keywords, HXB2 coordinates and (for ab) binding region/neutralizing classification for each match.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "table": "ctl",
      "epitope": "GGKKKYKLK"
    },
    "name": "immunology_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMaximum records to return (default 20, max 100), applied client-side after the upstream call.
tableYes"ctl" = CD8+ T-cell epitopes, "helper" = CD4+ T-cell epitopes, "ab" = antibody binding sites.
epitopeNoEpitope amino acid sequence, e.g. "GGKKKYKLK". Matches if this sequence is contained in the epitope.
mab_nameNoAntibody name or alias. "ab" table only.
protein_nameNoHIV protein name, e.g. "Gag", "Env", "Nef".

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / limit / description
      Previous value: -"Maximum records to return (default 20, max 100) — applied client-side after the upstream call."New value: +"Maximum records to return (default 20, max 100), applied client-side after the upstream call."
  2. First observed

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already cover read-only, open-world, idempotent and non-destructive, so the safety bar is met structurally; the description adds genuinely new context: queried LIVE against LANL's keyless JSON API, no ingest, always current (no auth needed, no staleness). It also states what each match carries (citation, keywords, HXB2 coordinates, binding region/neutralizing classification), which annotations cannot convey. It stops short of noting rate limits, error behavior, or upstream latency.

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?

Front-loaded with purpose and the sibling contrast before details, and every clause carries information. The example-question list is slightly long and partially overlaps with the table enumeration, so it is dense rather than perfectly lean.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema exists, and the description compensates by naming the returned fields per match and the differentiators between the three tables. With live-data provenance, required-input rules, and return contents all stated, an agent has everything needed to call and interpret this tool.

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 description coverage is 100%, so the baseline is 3, but the description adds meaning the schema does not enforce: it clarifies that table selects one of three distinct response shapes, and states 'at least one of mab_name, epitope, protein_name is required' — a constraint not captured by the schema's required list (only table). The only quibble is that this one-of constraint is stated in prose rather than reflected in the schema, and limit's client-side behavior is already in 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?

States a specific verb+resource (search the LANL HIV Molecular Immunology Database) and names the exact entity types returned (T-cell epitopes CTL/CD8+ or T-helper/CD4+, antibody binding sites). It explicitly contrasts with the sibling catnap_search_neutralization as 'where the immune response targets' vs 'how potently an antibody neutralizes', so an agent can distinguish the two without opening schemas.

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

Usage Guidelines5/5

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

Gives concrete example questions that map directly onto parameter combinations ('what CTL epitopes are in HIV Gag', 'which antibodies bind the CD4 binding site', 'find epitopes at position 296-331 of Env'). It also draws an explicit boundary against the nearest sibling, which is the key routing decision an agent faces here.

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.