Skip to main content
Glama
jshsakura

mfa-servicenow-mcp

by jshsakura

download_attachment

Download attachments from ServiceNow records to a local directory or retrieve remote links for access.

Instructions

Download attachments. Use saved_path locally; read the ResourceLink remotely when needed.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
tableNo
recordNoParent record: sys_id or display number (e.g. INC0010023).
filenameNoOverride saved name (single file only). Default: real file_name.
output_dirNoSave dir. Default: ./temp/<instance>/attachments/
max_size_mbNo
download_allNoIf the record has many attachments, fetch all (else list them).
attachment_sys_idNosys_attachment sys_id. Omit to resolve via table+record.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.18.41

TDQS

C2.4/5.0
Behavior2/5

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

With no annotations provided, the description carries the full behavioral burden and largely fails: no mention of auth/permission requirements, no indication of what saved_path or ResourceLink actually are, no disclosure of whether many-attachment records list or fetch, and no default-path expectations despite the schema defaulting to ./temp/<instance>/attachments/.

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

Conciseness3/5

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

Two short sentences, appropriately sized and front-loaded with the core action. However, the second sentence spends its length on undefined concepts instead of earning its place with usable detail.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 7-parameter tool with no annotations and no output schema, the description is far too thin. It omits the sourcing model (table+record vs attachment_sys_id), the list-vs-download behavior, and what the caller receives, none of which are covered by structured fields.

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

Parameters2/5

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

Schema coverage is 71% and the schema itself documents record, filename, output_dir, download_all, and attachment_sys_id well. The description adds no parameter meaning and instead introduces 'saved_path' and 'ResourceLink' — terms that correspond to no schema property, so it confuses rather than informs.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource (download attachments), but never says from where (ServiceNow records) or which attachments beyond a vague 'attachments'. It competes with siblings like export_record_xml and download_app_sources without any distinguishing scope, leaving the agent to infer from the schema that this is record-attachment retrieval.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The second sentence gestures at local-vs-remote usage ('Use saved_path locally; read the ResourceLink remotely'), but neither term maps to any parameter or sibling tool, so it gives no actionable when-to-use guidance. It also never mentions the download_all/attachment listing branch as a selection criterion.

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