Skip to main content
Glama

Amalgix

by io.amalgix

Analyze Document

analyze_document
Read-onlyIdempotent

Analyze a document using Crucible™ Evidence Engine. Returns source-grounded findings with evidence, confidence, verification status, and routing metadata. Use specialized financial/contract tools when the domain is known.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryYesAnalysis question or focus area
formatNoOptional: Force a specific input format. Default: auto-detect via magic bytes.
tickerNoOptional ticker/company symbol metadata for financial filing analysis.
contentNoDocument content to analyze (max 20MB). Required unless fileUrl is provided. Accepts: (1) plain text, (2) Base64-encoded file with data URI prefix (e.g., "data:application/pdf;base64,..."), or (3) raw Base64 binary for text-extractable source documents. PRIVACY NOTICE: Content is transmitted to third-party LLM providers for processing. Do NOT submit documents containing passwords, private keys, SSNs, or other regulated PII.
fileUrlNoOptional: HTTPS URL to download the document from. If provided, content field is ignored. Use text-extractable source documents. Max 20MB.
sourceTypeNoOptional source type metadata for Crucible™ routing and output metadata.
analysisTypeNoOptional Crucible™ analysis mode. Default: auto.
jurisdictionNoOptional contract jurisdiction metadata. Output remains evidence triage, not legal advice.
partyPerspectiveNoOptional contract review perspective. Default: neutral.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
metaYesProcessing metadata
analysisYes

Schema Changelog

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

  1. Changed13 schema fields changed
    • addedInput schema / properties / analysisType
      Added value: +{
+  "description": "Optional Crucible™ analysis mode. Default: auto.",
+  "enum": [
+    "auto",
+    "general_evidence",
+    "financial_filing",
+    "contract_review"
+  ],
+  "type": "string"
+}
    • changedInput schema / properties / content / description
      Previous value: -"Document content to analyze (max 20MB). Accepts: (1) plain text, (2) Base64-encoded file with data URI prefix (e.g., \"data:application/pdf;base64,...\"), or (3) raw Base64 binary. Supported binary formats: PDF, DOCX, XLSX, CSV. PRIVACY NOTICE: Content is transmitted to third-party LLM providers for processing. Do NOT submit documents containing passwords, private keys, SSNs, or other regulated PII."New value: +"Document content to analyze (max 20MB). Required unless fileUrl is provided. Accepts: (1) plain text, (2) Base64-encoded file with data URI prefix (e.g., \"data:application/pdf;base64,...\"), or (3) raw Base64 binary for text-extractable source documents. PRIVACY NOTICE: Content is transmitted to third-party LLM providers for processing. Do NOT submit documents containing passwords, private keys, SSNs, or other regulated PII."
    • changedInput schema / properties / fileUrl / description
      Previous value: -"Optional: HTTPS URL to download the document from. If provided, content field is ignored. Supports: PDF, DOCX, XLSX, CSV, HTML. Max 20MB."New value: +"Optional: HTTPS URL to download the document from. If provided, content field is ignored. Use text-extractable source documents. Max 20MB."
    • addedInput schema / properties / jurisdiction
      Added value: +{
+  "description": "Optional contract jurisdiction metadata. Output remains evidence triage, not legal advice.",
+  "maxLength": 80,
+  "minLength": 1,
+  "type": "string"
+}
    • addedInput schema / properties / partyPerspective
      Added value: +{
+  "description": "Optional contract review perspective. Default: neutral.",
+  "enum": [
+    "buyer",
+    "seller",
+    "vendor",
+    "customer",
+    "neutral"
+  ],
+  "type": "string"
+}
    • addedInput schema / properties / sourceType
      Added value: +{
+  "description": "Optional source type metadata for Crucible™ routing and output metadata.",
+  "enum": [
+    "text",
+    "file_url",
+    "upload_base64",
+    "public_url",
+    "ticker"
+  ],
+  "type": "string"
+}
    • addedInput schema / properties / ticker
      Added value: +{
+  "description": "Optional ticker/company symbol metadata for financial filing analysis.",
+  "maxLength": 16,
+  "minLength": 1,
+  "type": "string"
+}
    • changedInput schema / required
      Previous value: -[
-  "content",
-  "query"
-]New value: +[
+  "query"
+]
    • addedOutput schema / properties / analysis / properties / evidenceFindings
      Added value: +{
+  "description": "Normalized evidence findings with claim, evidence, sourceRef, confidence, and verificationStatus",
+  "items": {},
+  "type": "array"
+}
    • changedOutput schema / properties / analysis / properties / findings / description
      Previous value: -"Ranked findings with title, detail, and confidence"New value: +"Ranked evidence findings"
    • addedOutput schema / properties / meta / properties / analysisType
      Added value: +{
+  "type": "string"
+}
    • addedOutput schema / properties / meta / properties / engine
      Added value: +{
+  "type": "string"
+}
    • changedOutput schema / properties / meta / required
      Previous value: -[
-  "chunksProcessed",
-  "latencyMs",
-  "estimatedCost"
-]New value: +[
+  "estimatedCost"
+]
  2. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint. The description adds value by detailing the output structure (evidence, confidence, verification status, routing metadata) and including a privacy notice about third-party LLM processing, which goes beyond annotation information.

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?

Two sentences with clear front-loading: first sentence states purpose and output, second gives usage guidance. No wasted words, highly efficient.

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 the tool's complexity (9 parameters, output schema exists), the description covers purpose, output structure, usage guidance, and a privacy warning. It does not repeat schema details, which is appropriate. It could optionally mention the 20MB limit or supported formats, but those are in schema. Overall adequate.

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%, so baseline is 3. The description provides a global usage hint but does not add new parameter-specific meaning beyond what is already in the schema. The output description indirectly relates to query but not to individual parameters.

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 states it analyzes documents using the Crucible Evidence Engine and specifies the return type (source-grounded findings with evidence, confidence, etc.). It also advises using specialized tools when the domain is known, distinguishing it from siblings like analyze_public_filing and review_contract_risks.

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 explicitly says 'Use specialized financial/contract tools when the domain is known,' providing direct guidance on when not to use this tool and pointing to alternatives. It implies general usage for unknown domains but could be more specific about when to use this tool versus others like extract_web or summarize.

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

All Amalgix 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

A4.2/5.0
Disambiguation5/5

Each tool targets a distinct domain or action: document analysis, financial filings, contract review, translation, web extraction, summarization, cost estimation, and health check. Overlap is minimal and explicitly disambiguated in descriptions.

Naming Consistency5/5

All tool names follow a consistent verb_noun snake_case pattern (e.g., analyze_document, extract_web), making the set predictable and easy to navigate.

Tool Count5/5

With 8 tools, the server is well-scoped for a general-purpose AI toolkit, covering analysis, translation, extraction, summarization, and utilities without excess or deficiency.

Completeness4/5

The tool surface covers core workflows for document analysis, filings, contracts, translation, web extraction, and summarization. Minor gaps exist (e.g., no tool for editing or managing stored analyses), but the set is complete for its intended purpose.

Resources