Skip to main content
Glama

Hydrafetch

by com.hydrafetch
OverviewDiscussionsAdmin

Extract

extract
Read-only

Pull specific fields out of one or more pages as JSON, shaped by a JSON schema or described in a prompt. Use it when you need values such as prices, names or dates rather than the whole page text.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlsYesThe URLs to extract from.
promptNoNatural-language description of what to pull.
schemaNoA JSON schema the result must conform to.
showSourcesNoReturn the list of URLs that were actually extracted.
showConfidenceNoFor each field, return a confidence score and the exact source passage the value was drawn from.
preferStructureNoKeep headings, lists and tables in the text handed to the model.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / showConfidence
      Added value: +{
+  "description": "For each field, return a confidence score and the exact source passage the value was drawn from.",
+  "type": "boolean"
+}
    • addedInput schema / properties / showSources
      Added value: +{
+  "description": "Return the list of URLs that were actually extracted.",
+  "type": "boolean"
+}
  2. First observed

TDQS

A3.8/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, openWorldHint=true, and destructiveHint=false, so the safety profile is covered. The description adds that extraction is model-driven and constrainable by schema or prompt, but says nothing about cost, latency, rate limits, or failure behavior when a schema cannot be satisfied.

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, front-loaded with the core action and followed immediately by the selection criterion. No filler or restated field names.

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?

No output schema exists, but the description explains the return shape (JSON conforming to a provided schema, or prompt-derived) and that multiple URLs can be processed. Adequate for an agent to call correctly; only an edge case like schema-vs-prompt precedence is unaddressed.

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 the six parameters are already documented in the schema. The description mentions the schema/prompt duality but adds no syntax, precedence, or interaction guidance (e.g., whether prompt and schema can be combined) beyond the structured fields.

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 verb+resource ('Pull specific fields out of one or more pages as JSON') and the two shaping mechanisms (JSON schema or prompt). It implicitly distinguishes itself from the scrape sibling by contrasting with 'the whole page text', though it never names the alternative tool.

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 a clear when-to-use condition with concrete examples ('prices, names or dates rather than the whole page text'), which effectively routes the agent away from scrape/crawl for targeted value retrieval. No explicit when-not or named alternative, so it stops short of a 5.

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

All Hydrafetch toolsInspect
Try in Browser
Give agents eyes on the webHosted screenshot MCP. Send a URL, get a pixel-perfect image. $0.002 per grab. Works with Claude, Cursor, and Codex.grabbit.liveAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources