Skip to main content
Glama
SAP connector for Claude

SAP connector for Claude

get_attachments

List or download GOS attachments for an SAP document (invoice, PO, material doc, FI) by number, year, and company code, or via raw object type and key. Files save to Downloads; open them to view.

Instructions

GOS attachments of an SAP document: lists them and saves the files to Downloads/SAP attachments (content is never returned; open the saved file). kind: invoice (MIRO, needs year), material_doc (needs year), po, fi (needs year + company_code). Or raw object_type + object_key (e.g. BUS2091). download=false only lists.

Input Schema

NameRequiredDescriptionDefault
kindNo
yearNo
folderNo
numberNo
downloadNo
object_keyNo
object_typeNo
company_codeNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.7.7

TDQS

A4.2/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does disclose the critical side effect: files are written to 'Downloads/SAP attachments' and must be opened rather than read from the response. It omits whether existing files are overwritten, what permissions are needed, and how errors surface, which are real gaps for a tool that writes to disk.

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?

Three dense sentences, the core fact (files are saved, content not returned) front-loaded before the parameter rules. The kind-to-required-field mapping is compact and scannable, with no 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?

An output schema exists, so return values need not be explained, and the write-to-disk behavior plus the list-only mode are covered. Missing is any statement about the 'folder'/'number' inputs and about what list results look like when download=false, which leaves a small ambiguity for an 8-parameter tool.

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

Parameters3/5

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

Schema coverage is 0%, so the description must explain all 8 parameters, and it covers kind, year, company_code, object_type, object_key, and download well, including a concrete example (BUS2091). However, 'folder' and 'number' are never mentioned anywhere, leaving two of the eight inputs entirely undefined.

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 pair and resource ('GOS attachments of an SAP document: lists them and saves the files') and immediately clarifies the scope boundary that content is never returned. No sibling tool in the list touches SAP attachments, so an agent can route here unambiguously.

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?

Gives concrete selection rules among the parameter strategies: kind=invoice/material_doc/po/fi with the required companion fields (year, company_code), or the raw object_type + object_key alternative, plus the 'download=false only lists' switch. It does not say when to prefer the kind route over the raw route or what happens if all parameters are omitted.

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