Skip to main content
Glama

Raw Blackboard API request

bb_raw_request

Call any Blackboard API path on the configured instance for operations not covered by dedicated tools; write methods require BB_ALLOW_WRITES=1 and confirm:true.

Instructions

Escape hatch: call any Blackboard API path on the configured instance, for operations not covered by a dedicated tool. GET is always allowed; POST/PUT/PATCH/DELETE require BB_ALLOW_WRITES=1 and confirm:true. Returns the parsed JSON response.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "path": "<path>"
    },
    "name": "bb_raw_request"
  }
}

Input Schema

NameRequiredDescriptionDefault
bodyNoJSON request body for write methods
pathYesAbsolute API path, e.g. /learn/api/v1/courses/_123_1/contents/ROOT/children
queryNo
methodNo
confirmNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.6/5.0
Behavior4/5

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

Annotations only declare readOnlyHint=false and openWorldHint=false; the description adds the gating mechanics that matter (environment flag plus confirm:true for POST/PUT/PATCH/DELETE) and states the return shape (parsed JSON). It stops short of warning that DELETE-style calls are irreversible or describing error/failure responses, which is a real gap for a write-capable tool. No contradiction with the annotations, which correctly mark it as non-read-only.

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 short sentences, front-loaded with the escape-hatch framing and the method rules, with zero filler. Every clause conveys a distinct operational fact.

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?

For a 5-parameter, nested-object, write-capable tool with no output schema, the definition covers purpose, usage boundary, gating preconditions, and return format. What remains thin is query/body encoding guidance and failure-mode behavior, both of which an agent would benefit from here.

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?

With only 40% schema coverage, the description carries needed weight: it explains that path is an absolute API path on the configured instance and that method determines both permission gating and the need for confirm:true, semantics the schema does not express on its own. The query and body parameters remain unexplained in the description, so it does not fully close the coverage gap.

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?

"Escape hatch: call any Blackboard API path on the configured instance" states a specific verb, resource, and scope, and immediately frames it as the fallback for paths with no dedicated tool. An agent can distinguish this from bb_get_course, bb_create_page, etc. without opening any schema.

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

Usage Guidelines5/5

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

It gives both the when and the when-not: use it "for operations not covered by a dedicated tool," which explicitly routes the agent to the 30+ named siblings first. The allowed methods and their preconditions (GET always allowed; writes need BB_ALLOW_WRITES=1 and confirm:true) further constrain when invocation will succeed.

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