Paperboy

Official

Overview Schema Source Related Servers Discussions Admin

export_tables

DestructiveIdempotent

Save each table found in a PDF as a separate CSV file that opens cleanly in Excel, with optional formula escaping and overwrite control. Use it to turn PDF tables into spreadsheet data.

Instructions

Save the tables extract_tables finds as CSV files (UTF-8, readable by Excel), one per table, named page001-table01.csv and so on, in a folder (default: "_tables" next to the PDF). Spreadsheets run cells starting with = + - @ (or their full-width forms) as formulas, so such cells get a leading apostrophe unless escape_formulas=false (plain numbers like -5 are left alone). Limits and pages_skipped are as for extract_tables. Nothing is written if a file exists, unless overwrite. Needs the owner password if the PDF forbids copying.

Any password argument can be "ask": the user then types it on a local page, so it never passes through the chat.

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": {
      "input_path": "<input_path>"
    },
    "name": "export_tables"
  }
}

Input Schema

Name	Required	Default
`pages`	No
`password`	No
`strategy`	No	lines
`overwrite`	No
`input_path`	Yes
`max_tables`	No
`output_dir`	No
`escape_formulas`	No

Output Schema

Name	Required	Description	Default
`files`	Yes
`complete`	Yes
`truncated`	Yes
`output_dir`	Yes
`pages_skipped`	Yes
`pages_searched`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Addedv0.1.1Nov 12, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Goes well beyond the annotations: it discloses the apostrophe-escaping rule for formula-leading cells and the escape_formulas override, the no-clobber default unless overwrite, the need for an owner password when copying is forbidden, and the 'ask' out-of-band password flow. These details explain exactly why destructiveHint=true and idempotentHint=true hold.

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

Conciseness4/5

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

Front-loaded with the core action and artifact, then layered detail in compact parentheticals. Some sentences are dense and stack multiple conditions, but each contributes concrete behavior rather than filler.

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?

For a destructive, file-writing tool this covers output naming, collision policy, escaping, and authentication, and the output schema handles return values. The only shortfall is the undocumented 'strategy' parameter, which an agent would have to guess at.

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

Parameters4/5

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

With 0% schema coverage and 8 parameters, the description carries the burden and mostly delivers: it explains output_dir and its default, overwrite, escape_formulas with the -5 exception, password with the 'ask' sentinel, and password escalation to owner password. The 'strategy' parameter is never mentioned, leaving one meaningful knob undocumented.

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?

States a specific verb and output format ('Save the tables extract_tables finds as CSV files'), including file naming and location. It pairs explicitly with extract_tables and is distinguishable from export_markdown by naming CSV tables as the artifact.

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 clearly frames this as the follow-up step to extract_tables and inherits its 'Limits and pages_skipped' semantics, giving the agent a clear context for use. It never names an alternative or a when-not condition (e.g., when to prefer a markdown export instead), so it stops short of full routing guidance.

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