Skip to main content
Glama

smart-data-extractor

by io.github.lazymac2x

batch_extract

Idempotent · 30s timeout · Extract data from multiple sources (JSON/JSONL/text) with a single consistent schema. Pass idempotency_key to deduplicate within 5 minutes.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
schemaNoOptional target JSON Schema (draft-07) applied to all sources. If omitted, inferred from first source and reused across remaining sources. Enables consistent field extraction from diverse formats.
sourcesYesArray of 1-100 data sources to extract from. Each source includes type (format) and content (raw data).
idempotency_keyNoOptional deduplication key (UUID/string) for 5-minute cache. Identical batch calls (same sources + schema + key) return cached results instantly.

Schema Changelog

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

  1. Changed10 schema fields changed
    • addedInput schema / additionalProperties
      Added value: +false
    • changedInput schema / properties / idempotency_key / description
      Previous value: -"Optional client-supplied key for dedup within 5min cache"New value: +"Optional deduplication key (UUID/string) for 5-minute cache. Identical batch calls (same sources + schema + key) return cached results instantly."
    • changedInput schema / properties / schema / description
      Previous value: -"Optional target JSON Schema. If omitted, auto-inferred from first source."New value: +"Optional target JSON Schema (draft-07) applied to all sources. If omitted, inferred from first source and reused across remaining sources. Enables consistent field extraction from diverse formats."
    • changedInput schema / properties / sources / description
      Previous value: -"Array of data sources (objects with type + content)"New value: +"Array of 1-100 data sources to extract from. Each source includes type (format) and content (raw data)."
    • addedInput schema / properties / sources / items / additionalProperties
      Added value: +false
    • changedInput schema / properties / sources / items / properties / content / description
      Previous value: -"The raw content to extract from"New value: +"Raw source content (max 200KB per source). For jsonl: each line must be valid JSON. For text: format \"key1:value1,key2:value2\"."
    • changedInput schema / properties / sources / items / properties / type / description
      Previous value: -"Source format: json (single object/array), jsonl (newline-delimited), text (key:value pairs)"New value: +"Source format: \"json\" (single object or array), \"jsonl\" (newline-delimited JSON objects), \"text\" (key:value pairs delimited by commas/semicolons)"
    • changedInput schema / properties / sources / items / properties / type / enum
      Previous value: -[
-  "json",
-  "text",
-  "jsonl"
-]New value: +[
+  "json",
+  "jsonl",
+  "text"
+]
    • addedInput schema / properties / sources / maxItems
      Added value: +100
    • addedInput schema / properties / sources / minItems
      Added value: +1
  2. Changed5 schema fields changed
    • addedInput schema / properties / idempotency_key
      Added value: +{
+  "description": "Optional client-supplied key for dedup within 5min cache",
+  "type": "string"
+}
    • changedInput schema / properties / schema / description
      Previous value: -"Target schema for extraction"New value: +"Optional target JSON Schema. If omitted, auto-inferred from first source."
    • changedInput schema / properties / sources / description
      Previous value: -"Array of data sources"New value: +"Array of data sources (objects with type + content)"
    • addedInput schema / properties / sources / items / properties / content / description
      Added value: +"The raw content to extract from"
    • addedInput schema / properties / sources / items / properties / type / description
      Added value: +"Source format: json (single object/array), jsonl (newline-delimited), text (key:value pairs)"
  3. First observed

TDQS

A4.2/5.0
Behavior4/5

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

It discloses idempotency, a 30-second timeout, and a 5-minute deduplication window, which are key behavioral traits not otherwise present in annotations or schema. It does not cover error handling or partial failure behavior, which leaves some gaps for an extraction tool with no annotations.

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 a single, scannable sentence with key attributes front-loaded (idempotency, timeout) followed by the core purpose. Every element is purposeful with no 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 the absence of an output schema, the description could have hinted at the return type, but it provides essential operational context (timeout, idempotency, dedup). The rich input schema compensates for details about source limits and formats.

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 has 100% coverage with detailed parameter descriptions, so the description adds only marginal value by referencing the consistent schema and idempotency_key. The schema itself fully explains the sources, schema, and idempotency_key semantics.

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 the tool extracts data from multiple sources (JSON/JSONL/text) with a single consistent schema. It uses a specific verb 'Extract' and names the resource, distinguishing it from siblings like extract_from_api or extract_from_url.

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 implies use for batch extraction from multiple sources with a unified schema, which gives clear context. However, it does not explicitly state when to prefer this tool over alternatives or list exclusions.

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

All smart-data-extractor 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

A4/5.0
Disambiguation4/5

The tools are mostly distinct: auto_schema_learn is clearly separate as it only infers schemas, while extract_from_api and extract_from_url differ by source type. batch_extract covers multi-source extraction but could overlap with single-source tools in certain scenarios. No two tools are truly indistinguishable.

Naming Consistency3/5

Naming is a mix of patterns: extract_from_api and extract_from_url share a consistent 'extract_from_X' form, but batch_extract uses an adjective+verb structure, and auto_schema_learn places the verb last. All use snake_case, which is readable, but the lack of a uniform verb_noun pattern is noticeable.

Tool Count5/5

Four tools is an ideal scope for a data extraction server, covering schema inference, single-source extraction from API and URL, and multi-source batch extraction. Each tool has a clear purpose, and the count is neither too thin nor too heavy.

Completeness4/5

The tool surface covers the core domain well: schema learning, extraction from API and URL, and batch extraction from multiple formats on a consistent schema. Minor gaps include no dedicated text extraction tool (though batch handles it) and no explicit output formatting options, but common workflows are fully supported.

Resources