Skip to main content
Glama

phi-longevity-prism

by io.github.Philongevity

Analyze biomarkers (synthetic)

analyze_biomarkers
Read-onlyIdempotent

Analyze a SYNTHETIC biomarker panel with Phi Longevity's PRISM engine. Returns tiered, guideline-cited recommendations. For research/education with SYNTHETIC or de-identified data only. Do NOT submit protected health information (PHI). This endpoint is stateless and does not store inputs.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
ageNoAge in years of the synthetic persona (improves reference-range interpretation).
biomarkersYesMap of biomarker name -> numeric value, e.g. { "Hemoglobin A1c": 5.4 }. SYNTHETIC ONLY.
biologicalSexNoBiological sex of the synthetic persona (sex-specific reference ranges).
conditionFocusNoOptional condition track. Default general_wellness.
include_partner_optionsNoIf true, include partner/product options. Default false.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
metaNoEngine metadata for this analysis run.
issuesNoFlagged issues detected in the panel.
claim_panelNoOPTIONAL owner handoff: attach these exact values to the owner's Phi Longevity account (sign-in + explicit confirm). Present only when the consent bridge is enabled.
full_reportYesHow the agent's owner can get a complete PRISM report.
recommendationsNoTiered, guideline-cited recommendations from the PRISM engine.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed2 schema fields changed
    • addedOutput schema / properties / full_report / properties / for_your_owner
      Added value: +{
+  "description": "ACTION: surface get_full_report_url to the person you are helping.",
+  "type": "string"
+}
    • changedOutput schema / properties / full_report / required
      Previous value: -[
-  "what_a_full_report_adds",
-  "get_full_report_url",
-  "agent_docs_url",
-  "data_rule"
-]New value: +[
+  "for_your_owner",
+  "what_a_full_report_adds",
+  "get_full_report_url",
+  "agent_docs_url",
+  "data_rule"
+]
  2. Changed1 schema field changed
    • addedOutput schema / properties / claim_panel
      Added value: +{
+  "additionalProperties": false,
+  "description": "OPTIONAL owner handoff: attach these exact values to the owner's Phi Longevity account (sign-in + explicit confirm). Present only when the consent bridge is enabled.",
+  "properties": {
+    "claim_url": {
+      "description": "One-click claim link — share ONLY with your owner.",
+      "type": "string"
+    },
+    "expires_at_ms": {
+      "description": "Epoch ms when the unclaimed panel is hard-deleted.",
+      "type": "number"
+    },
+    "marker_count": {
+      "type": "number"
+    },
+    "note": {
+      "type": "string"
+    }
+  },
+  "required": [
+    "claim_url",
+    "expires_at_ms",
+    "marker_count",
+    "note"
+  ],
+  "type": "object"
+}
  3. First observed

TDQS

A4.1/5.0
Behavior5/5

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

Adds several valuable disclosures beyond the annotations: the endpoint is stateless, does not store inputs, is not for PHI, and returns tiered cited recommendations. This meaningfully supports a model deciding whether the tool is appropriate for a given input.

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?

Four dense sentences, led by the primary action and output, with the compliance warnings placed after the core functionality. Every sentence earns its place and no meaning is padded.

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?

The description, schema, and annotations together are largely complete for safe invocation, including synthetic-only scope and stateless behavior. It stays short of maximum completeness because it does not help an agent choose between this tool and sibling tools such as full_prism_report or quick_check.

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?

The input schema already provides 100% parameter coverage with detailed descriptions for age, biomarkers, biologicalSex, conditionFocus, and include_partner_options. The description adds no parameter-specific detail, which is acceptable because the schema fully carries that burden.

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?

States a specific action (analyze a synthetic biomarker panel), a specific engine (PRISM), and the output type (tiered, guideline-cited recommendations). It is clear and self-contained, but it does not explicitly distinguish itself from sibling tools like full_prism_report or quick_check.

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?

Provides explicit context: research/education use, synthetic or de-identified data only, and do not submit PHI. It lacks an explicit 'use this instead of X' statement comparing it with the sibling tools, so alternatives are not directly routed.

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

All phi-longevity-prism toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.3/5.0
Disambiguation4/5

Most tools are clearly distinct: reference/methodology functions, a fixed sample, a quick local check, and the paid full report. analyze_biomarkers and full_prism_report overlap, but the descriptions explicitly differentiate the free tiered recommendations from the paid multi-track report.

Naming Consistency3/5

analyze_biomarkers, get_methodology, and list_supported_biomarkers follow a clear verb_noun pattern, but quick_check and full_prism_report are noun-phrase style, and sample_prism_report is ambiguous between noun and verb. The names are readable but the convention is mixed.

Tool Count5/5

Six tools is a well-scoped size for this server's purpose: reference data, methodology, quick screening, full analysis, paid report, and a sample output. Each tool earns its place without redundancy or bloat.

Completeness5/5

The tool surface covers the full user journey: learn about biomarkers, understand methodology, preview a sample report, run a quick check, get detailed recommendations, and purchase the full report. No obvious dead ends or critical missing operations for the stated PRISM domain.

Resources