Skip to main content
Glama

extract

Converts web tables, lists, or forms into structured JSON with source and row IDs, optionally limiting columns and skipping previously seen rows.

Instructions

JSON table/list/form with source and row ids. fields: columns; new_only: skip seen rows.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "extract"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindNo
fieldsNo
withinNo
new_onlyNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

C2.4/5.0
Behavior2/5

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

No annotations are provided, so the description carries the full disclosure burden. It does reveal one behavioral fact beyond the schema — that output is JSON keyed with source and row ids — which is useful given there is no output schema. However, it says nothing about read-only vs mutation semantics, page state requirements, pagination, or failure modes, leaving the agent without the behavioral profile a 4-parameter extraction tool needs.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is short but cryptic rather than concise — a fragmentary clause chain with no clear subject or verb, following a name that is itself vague. Nothing is padded, but the terseness comes at the cost of comprehension, and the two parameter notes are buried mid-sentence without structure.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a four-parameter tool with zero annotation coverage, zero schema description coverage, and no output schema, this description is thin but not empty — it names the return shape and clarifies two parameters. Half the parameters and all behavioral traits remain undocumented, so it falls short of what the complexity warrants.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must supply all parameter meaning, and it explains only two of four: 'fields' as columns and 'new_only' as skipping seen rows. The 'kind' enum values (auto/table/list/form) and especially the integer 'within' are left completely opaque, which is a meaningful gap since 'within' could mean frame, depth, or distance.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The verb 'extract' is only implied; the description says it yields 'JSON table/list/form with source and row ids', which does convey that it pulls structured page data into JSON. But the phrasing is telegraphic and never distinguishes it from siblings like snapshot or screenshot, which could plausibly return page content too. An agent can guess the purpose but not confidently separate it from alternatives.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no statement of when to use this tool versus snapshot or screenshot, nor any prerequisite or sequencing guidance. The 'auto' value in the kind enum hints at automatic detection but the description never explains when to pick a specific kind. Usage must be inferred entirely from the name.

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

Deploy Server

Other Tools