Skip to main content
Glama

ai-netcafe

by com.ainetcafe

A batch of invoices → one ledger-ready table (arithmetic-checked)

extract_invoices
Read-onlyIdempotent

Give it up to 20 invoice URLs (PDF or page images) and get back one table ready to post: number, date, seller, buyer, net / tax / gross, currency. Every row is checked in code — net + tax must equal gross — and the batch total is re-added independently, so a row the model misread is flagged with the exact difference instead of quietly landing in your books. Mixed currencies get no batch total on purpose: adding them together would be an accounting error. CSV is UTF-8 with BOM so Excel opens it right.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlsYesInvoice URLs — comma-separated, or pass an array. Up to 20 per call.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

TDQS

A4.7/5.0
Behavior5/5

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

The description provides rich behavioral detail beyond the readOnlyHint and idempotentHint annotations: arithmetic validation (net+tax=gross), independent batch total re-addition, flagging misread rows with the exact difference, and deliberately omitting batch totals for mixed currencies to avoid accounting errors. It also specifies CSV encoding (UTF-8 with BOM) for Excel compatibility.

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 well-structured and front-loaded, starting with the action and constraint ('Give it up to 20 invoice URLs...'). Every sentence contributes essential information: input/output, validation logic, currency behavior, and CSV format. It is appropriately sized for the tool's complexity with no redundant 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?

Given the tool's moderate complexity and the existence of an output schema, the description covers all necessary context: input constraints (URLs, PDF/images, up to 20), processing behavior (arithmetic checks, error flagging), handling of mixed currencies, and output format (table fields, CSV encoding). It leaves no significant gaps in understanding.

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?

The schema already documents the only parameter 'urls' with details (comma-separated, array, up to 20 per call), achieving 100% coverage. The description adds meaning by specifying acceptable input formats (PDF or page images), which is not present in the schema, thus providing extra value beyond the structured definition.

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 uses a specific verb ('extract') and clearly states the input (invoice URLs) and output (a ledger-ready table with number, date, seller, buyer, net/tax/gross, currency). It distinguishes itself from siblings like extract_tables by focusing on invoice-specific arithmetic checks and ledger readiness.

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 conveys the use case: batch-processing invoices into a ledger-ready table. It doesn't explicitly name alternatives or exclusions (e.g., 'use extract_tables for non-invoice tables'), but the context is unambiguous and sufficient for an agent to decide when to invoke this tool.

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

All ai-netcafe toolsInspect
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

A3.6/5.0
Disambiguation3/5

Many tools are clearly distinct, but there are several overlapping groups: PDF extraction (extract_invoices, extract_statement, extract_tables, pdf_to_markdown), table comparison (diff_tables vs reconcile_ledger), and model pricing (list_models vs model_costs). Descriptions help clarify boundaries, but an agent could misselect without careful reading.

Naming Consistency3/5

All names use lowercase snake_case, but the verb-noun pattern is inconsistent. Most tools are verb-first (build_app, clean_table, fetch_page), but several are noun-first (jwt_decode, regex_test, web_search), noun-only (ai_visibility, model_costs), bare verbs (recall, remember), or a full phrase (what_can_you_do). This mixed convention is still readable but not predictable.

Tool Count2/5

With 34 tools, this server exceeds the 25-tool threshold for 'too many'. While the breadth covers many utility domains, the count is heavy and some tools could be consolidated or removed. A more focused set would reduce cognitive load and misselection risk.

Completeness3/5

The utility set covers web, PDF, CSV, model, task, and dev tooling well, but there are notable gaps in resource lifecycles. Apps have build/list/get but no update/delete, and memories support remember/recall but no forget. These missing operations could create dead ends for agents.

Resources