Skip to main content
Glama
Sign In

Krawlup

by com.krawlup
OverviewDiscussionsAdmin

generate_content_draft

Triggers one grounded blog-post draft for a product (Content Lab). Generated ONLY from the product's own Krawlup facts — profile, tracked prompts, tracked keywords, triaged mentions; never auto-published, the founder reviews and copies the markdown into their own blog. Angles: prompt-answer (answer a tracked AI question that does not cite the product yet — pass the exact prompt text as sourceRef), comparison (honest vs-post; topic names the rival, unverified rival claims stay neutral), mention-answer (answer a real community mention — pass the term as sourceRef), custom. The draft flips from generating to ready (or honestly failed) in the dashboard's Content tab within a few minutes. Requires a key with the rescan scope

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": {
      "productKey": "<productKey>",
      "type": "<type>",
      "topic": "<topic>"
    },
    "name": "generate_content_draft"
  }
}

Input Schema

NameRequiredDescriptionDefault
typeYesThe draft angle
topicYesWhat the post is about, one line (e.g. "best lightweight alternative to Acme for solo founders")
sourceRefNoThe grounding anchor when one exists: the exact tracked prompt text or the watch term
productKeyYesThe product key (see list_products)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already mark this as a non-read-only, non-destructive, non-idempotent write, and the description adds substantial context beyond that: grounding is restricted to the product's own facts, nothing is auto-published, a human copies the markdown manually, and the job transitions asynchronously to ready or honestly failed within minutes. It also discloses the required rescan scope.

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?

The core action and constraints are front-loaded, and nearly every clause carries operational information. The single dense block with dashes and semicolons is slightly harder to scan than a short bulleted structure would be, but it is not padded.

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?

For an async generation tool with no output schema, the description covers what is generated, what grounds it, what happens after the call, where to observe status, and the auth scope required. An agent has enough to call it correctly and set expectations for the result.

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 the baseline is 3, but the description adds real meaning for sourceRef: it is the grounding anchor and must be the exact tracked prompt text for prompt-answer or the watch term for mention-answer. It also clarifies that topic should name the rival for comparison drafts, going beyond the schema's generic one-line description.

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: 'Triggers one grounded blog-post draft for a product (Content Lab).' It immediately scopes the output as generated only from the product's own Krawlup facts and explicitly says it is never auto-published, which separates it from any write/publish sibling.

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?

Gives explicit per-angle conditions: prompt-answer requires a tracked AI question that does not cite the product yet, comparison requires a rival named in the topic, mention-answer requires a real community mention. It also states the prerequisite of a key with the rescan scope, leaving little to inference.

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

All Krawlup toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources