Skip to main content
Glama
spidra-mcp-server

spidra-mcp-server

Official
by spidra-io

spidra_crawl_extract

Extract new data from every page saved by a finished crawl without revisiting the site, saving crawl costs while charging only AI credits. Returns a new jobId to track with spidra_get_job.

Instructions

Run a new extraction over every page a finished crawl saved, without visiting the site again. Much cheaper than crawling again: only AI credits are charged. Returns a new "jobId"; check it with spidra_get_job (type "crawl"). The original crawl doesn't change.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "jobId": "<jobId>",
      "transformInstruction": "<transformInstruction>"
    },
    "name": "spidra_crawl_extract"
  }
}

Input Schema

NameRequiredDescriptionDefault
jobIdYesThe finished crawl's jobId
transformInstructionYesWhat to extract from every page

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.7.0
    • changedInput schema / properties / jobId / description
      Previous value: -"The completed source crawl job id"New value: +"The finished crawl's jobId"
    • changedInput schema / properties / transformInstruction / description
      Previous value: -"The new extraction instruction to apply to every crawled page"New value: +"What to extract from every page"
  2. First observedv0.2.2

TDQS

A4.7/5.0
Behavior5/5

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

Annotation set (readOnlyHint=false, destructiveHint=false) already signals a non-destructive write; the description adds substantive context beyond it: no network re-visit, cost model (AI credits only), asynchronous job creation, and that the source crawl is left unmodified. That is exactly the behavior an agent needs before choosing this over a re-crawl.

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?

Three short sentences, front-loaded with the action and scope, then cost rationale, then the return value and next step. No filler.

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?

With no output schema, the description still names the return value (a new jobId) and the tool to poll it with, and it clarifies cost and side effects. For a 2-parameter async job tool, that covers everything needed to call it correctly.

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 coverage is 100% and both parameters are documented there, so baseline is 3. The description only lightly reinforces usage — 'every page a finished crawl saved' implies jobId must reference a completed crawl — but adds no format or constraint detail beyond 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?

Specific verb+resource: 'Run a new extraction over every page a finished crawl saved'. It explicitly distinguishes itself from re-crawling ('without visiting the site again'), which separates it from spidra_crawl and spidra_scrape.

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?

States the condition (a finished crawl exists), the tradeoff against the alternative ('Much cheaper than crawling again: only AI credits are charged'), and the follow-up routing ('check it with spidra_get_job (type "crawl")'). Implicitly it tells the agent to use spidra_crawl only when new pages are needed.

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