AI NetCafé

PDF tables → structured rows (with schema alignment)

extract_tables

Read-onlyIdempotent

Extract tables from a PDF into structured rows (JSON + CSV). Pass fields to force a fixed set of columns — that aligns a pile of documents that each name their headers differently into one consistent table. Rows the model was unsure about are flagged rather than guessed. Text-layer PDFs only.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`url`	Yes	Public URL of the PDF.
`fields`	No	Optional comma-separated target columns, e.g. "invoice_no,supplier,date,amount". Omit to infer from the header.

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

TDQS

A4.7/5.0

Behavior5/5

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

Beyond the readOnlyHint and idempotentHint annotations, the description discloses that uncertain rows are flagged rather than guessed, which is a key behavioral detail affecting output trust. It also explicitly limits input to 'text-layer PDFs only', a critical constraint not captured by 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 three succinct sentences: core function, optional parameter use case, and a caveat. It is front-loaded with the primary action and no redundant wording. Every sentence contributes useful information.

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?

Given the tool has only two parameters, both fully described, an output schema, and annotations covering safety, the description covers purpose, optional behavior, and a key constraint. It appropriately relies on the output schema for return value details, so no additional explanation is needed.

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?

Schema coverage is 100% with descriptions for both parameters, providing a solid baseline. The description adds semantic meaning to 'fields' by explaining its purpose in aligning differently-named headers into a consistent table, going beyond the schema's generic 'target columns' description. The 'url' parameter is self-explanatory.

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 begins with a specific verb and resource: 'Extract tables from a PDF into structured rows (JSON + CSV).' It clearly distinguishes the tool from siblings by highlighting 'schema alignment' and 'text-layer PDFs only', which narrows its scope uniquely among similar tools like extract_statement.

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 provides a clear context for use: extracting tables from PDFs, with an optional 'fields' parameter to force consistent columns when documents have varying headers. It also states the text-layer restriction, which serves as a prerequisite. However, it does not explicitly name alternative tools or state when not to use this tool, but the guidance is sufficient for basic selection.

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

All AI NetCafé tools Inspect

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

A3.9/5.0

Disambiguation5/5

Every tool has a clearly distinct purpose with detailed descriptions that explicitly differentiate even close pairs like diff_tables vs reconcile_ledger and list_models vs model_costs. No two tools appear to do the same thing, and the what_can_you_do tool further resolves any confusion.

Naming Consistency3/5

The majority of tools follow a verb_noun snake_case pattern (build_app, fetch_page, list_tasks), but several notable deviations exist: ai_visibility, china_reachability, model_costs, json_yaml, pdf_to_markdown, what_can_you_do, recall, remember, and jwt_decode. This mixed convention, while still readable, is not fully consistent.

Tool Count3/5

With 34 tools, the count is high and exceeds the typical comfortable range for an MCP server. However, the server is a broad AI utility platform covering web, data, LLM, conversion, and scheduling tasks, and each tool appears to serve a distinct purpose with little redundancy, making the large but organized set borderline appropriate for its scope.

Completeness3/5

The tool surface covers a wide array of common workflows (search, fetch, table operations, PDF extraction, model comparisons, task scheduling, memory). However, check_job references deep_research, translate_pdf, and make_slides which are not present in the tool list, and there is no update tool for tasks/apps or a way to delete memories, leaving some user journeys incomplete.

Resources

Need Help?