Skip to main content
Glama

YouSpot

by com.youspot

Read invoice PDF

parse_invoice_pdf
Read-only

Read an invoice PDF the user uploaded and return its fields: supplier, invoice number, dates, currency, subtotal, tax, total, PO number, payment terms, and every line item. Use it whenever someone asks what an invoice says, what they are being charged for, whether a bill adds up, or wants an invoice turned into data.

Two parts of the result matter more than the fields. unreadable names what could not be read off the document — those are null, not guessed, and you must not fill them in yourself. checks lists where the document disagrees with itself: lines that do not sum to the subtotal, a total that is not subtotal plus tax, a quantity times a price that is not the line amount. Report every check to the user in plain language; they are the reason to read an invoice with a tool rather than an eye.

Find the file first with search_graph_objects (type 'file') and pass its object_id, or pass part of the filename as name.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameNoPart of the filename, when the object_id is unknown.
object_idNoThe file's graph object_id.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Beyond the readOnlyHint annotation, the description discloses critical behaviors: unreadable fields are null and must not be guessed, and checks surfaces internal inconsistencies that must be reported to the user. This gives the agent a clear model of the tool's output semantics and obligations.

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?

The description is longer than average but earns its length by covering purpose, special output fields, user obligations, and parameter usage. The structure front-loads the main purpose and then explains the non-obvious parts. Only the final rhetorical sentence could be trimmed without losing essential 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?

For a tool with no output schema, the description thoroughly explains what fields are returned and what the special unreadable and checks fields mean. It also covers how to identify the target file, making it nearly self-sufficient for correct invocation.

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%, so both parameters are documented. The description adds value by explaining how to populate them: find the file with search_graph_objects and pass object_id, or pass part of the filename as name. This is a meaningful supplement to 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?

The description opens with a specific verb and resource: 'Read an invoice PDF... and return its fields', then enumerates the exact fields returned. This clearly distinguishes the tool from generic file-reading siblings like read_file by focusing on invoice-specific structured extraction.

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 explicitly states when to use the tool: 'Use it whenever someone asks what an invoice says, what they are being charged for, whether a bill adds up, or wants an invoice turned into data.' It also gives practical guidance for finding the file via search_graph_objects, though it does not explicitly mention when not to use it or compare it to read_file.

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

All YouSpot 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

A3.8/5.0
Disambiguation4/5

Most tools are scoped to a distinct resource and action, and descriptions do a good job separating close pairs like search_connections vs ask_about_connections or get_my_linkedin_posts vs linkedin_analytics. However, the multiple deletion tools (delete_graph_object, delete_graph_objects, purge_graph_object) and the several file-reading tools are easy to confuse without reading the descriptions carefully.

Naming Consistency4/5

The vast majority of tools follow a clear verb_noun pattern such as create_, get_, list_, search_, send_, and delete_. A handful of noun-phrase outliers like linkedin_analytics, mutual_connections, top_message_correspondents, and what_needs_attention break the pattern, so it is highly consistent but not perfect.

Tool Count1/5

64 tools is an extreme count, far beyond the typical well-scoped 3-15 tool range and even beyond the 25+ threshold for 'too many'. While the server covers many integrations, this many tools creates a heavy navigation burden and would be better split into focused servers per domain.

Completeness3/5

Core graph/CRM operations and read-side integration coverage are strong, with search, get, list, and create tools across most domains. However, there are notable dead ends: no delete_calendar_event, no tracker management beyond create_tracker, and set_follow_up explicitly lacks a read-back query tool, so some natural user requests cannot be completed through the toolset.

Resources