Skip to main content
Glama

Create a knowledge hub

create_knowledge_hub

Use this when the organization has no knowledge hub yet and the user wants AI-written steps to draw on their websites and notes. Builds a hub from up to 20 websites and 50 notes in the background: it answers at once with the hub still processing, so read the hub until its status is complete. An organization has one hub, and a second is refused. Free.

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": {
      "websites": "<websites>"
    },
    "name": "create_knowledge_hub"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNoThe hub's name. Left out, one is taken from what is read.
notesNoUp to 50 notes the pages are also written from.
websitesYes1 to 20 sites, read in the background into one set of pages. A site that cannot be read is no error: its `lastCrawledAt` stays absent.

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.4/5.0
Behavior5/5

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

Adds substantial behavior beyond annotations: the build runs in the background, the call answers immediately while processing continues, the agent must re-read the hub until status is complete, only one hub per org is allowed, and an unreadable site is not an error (its lastCrawledAt stays absent). This is exactly the async/polling context the annotations cannot convey.

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?

Usage condition is front-loaded, then limits, then the async/polling behavior, with no filler sentences. The trailing 'Free.' fragment is terse but does carry a cost signal an agent may need when recommending the tool.

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?

No output schema exists, and the description compensates by explaining that the response arrives while processing continues and that the agent should re-read the hub for status. Combined with the 100%-covered schema, an agent has everything needed to call it and follow up correctly.

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 description coverage is 100%, so parameters are already documented, including defaults for isCompetitor, includeSubPages and filename uniqueness. The description only restates the 20-site/50-note caps, adding little meaning beyond 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?

States a specific verb and resource (create a knowledge hub) and immediately bounds it: built from up to 20 websites and 50 notes, with AI-written pages. It is clearly distinguishable from get/update/delete/list_knowledge_hub siblings.

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 an explicit precondition for use: the organization must have no hub yet and the user wants AI-written steps drawn from websites and notes, and notes that a second hub is refused. It does not name a specific alternative tool, but the when-not condition is stated plainly.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources