Skip to main content
Glama
alanwtom

blackboard-mcp

by alanwtom
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Get Blackboard course attachment

get_attachment
Read-only

Download a Blackboard course file and return its text content plus local save path. Long files support pagination via offset.

Instructions

Download a course file (PDF, Word, PowerPoint, Excel, notebooks, text, images, ...) from Blackboard and return its contents as text, plus the local path where it was saved (~/.blackboard-mcp/downloads). PDFs come back page by page, slides with speaker notes, spreadsheets as CSV per sheet. Long files come in pages: pass next_offset back as offset to keep reading. Nothing is sent anywhere. Read-only.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
offsetNoCharacter offset to continue a long file (from next_offset).
file_idNoWhich file, when a content item has several (a file_id or file_name from available_files).
course_idYesBlackboard course id from list_courses, e.g. "_26184_1" (course code also accepted).
content_idYesBlackboard content id from get_course_content or get_assignments, e.g. "_3001_1".

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.2.0
    • changedInput schema / properties / file_id / description
      Previous value: -"Specific file id when a content item has several attachments (see available_files in the result)."New value: +"Which file, when a content item has several (a file_id or file_name from available_files)."
    • addedInput schema / properties / offset
      Added value: +{
+  "description": "Character offset to continue a long file (from next_offset).",
+  "minimum": 0,
+  "type": "integer"
+}
  2. First observedv0.1.0

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint and openWorldHint, yet the description still adds real value: the save location (~/.blackboard-mcp/downloads), per-format extraction semantics (pages, speaker notes, CSV per sheet), pagination via next_offset, and the privacy note that nothing is sent anywhere. Only 'Read-only' is redundant with the annotations.

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?

Front-loaded with the core action and return shape, then format specifics and pagination. Four sentences, all relevant, with no filler; slightly dense but nothing that should be cut.

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?

With no output schema, the description carries the return-value burden and does so: it describes the text payload, the saved path, per-format structure, and how to continue long files. An agent can call this correctly and interpret the result without further documentation.

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 parameters are already documented; the description goes further by explaining the offset/next_offset continuation loop and the multi-file case (file_id/file_name from available_files). It adds semantics the schema cannot, though it references a 'next_offset' field not present in the input 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?

States a specific verb ('Download') and resource ('a course file ... from Blackboard') plus the return form (text contents + local save path). This is clearly distinguishable from siblings like read_link or get_course_content, which fetch pages/links rather than file bodies.

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 clear operating context: the supported file types, the local path where files land, and the pagination contract ('pass next_offset back as offset to keep reading'). It never names when to prefer this over a sibling such as read_link, so it stops short of explicit alternatives/exclusions.

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

Deploy Server

Other Tools