SupaBird

generate_ideas

This tool starts a background job and returns a job_id immediately — it does NOT return posts directly. After calling this you MUST call check_ideas_status with the returned job_id and keep polling until status is 'completed' or 'failed'. Tell the user generation is in progress while you wait.

Generate new X/Twitter post ideas using the current Ideas Lab engine (two modes only). Generation often takes 1–3 minutes — after this tool returns a job_id you MUST keep calling check_ideas_status until completed or failed. Do not stop after 30 seconds.

IMPORTANT: Before calling this tool, always ask the user for any missing required information. Do not make assumptions or use defaults.
Do NOT offer deprecated options: remix, niche, viral, or myPosts.

Required information to collect:
1. **Writing style** — exactly one of:
- "myStyle": write in the user's personal tone
- "creators": write in a chosen creator's style

2. **Idea source** — exactly one of:
- "user": ideas from the user's own posts
- "creator": ideas from a chosen creator

3. **Number of posts** — how many ideas to generate (5–20).

4. **Creators** — required when ideaSource is "creator" OR writingStyle is "creators". At least one X/Twitter username (without @).

Only call this tool once you have all required answers from the user.

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": {
      "writingStyle": "<writingStyle>",
      "ideaSource": "<ideaSource>"
    },
    "name": "generate_ideas"
  }
}

Input Schema

Name	Required	Description
`creators`	No	X/Twitter usernames (without @). Required when ideaSource is 'creator' or writingStyle is 'creators'. Example: ['naval', 'paulg']
`ideaSource`	Yes	Where ideas come from. 'user' = the user's own posts. 'creator' = a chosen creator. Do not use niche, viral, or myPosts.
`social_set`	No	The social set (brand) this is for: its name, id or one of its handles. Omit when the user has one set.
`writingStyle`	Yes	Writing style. 'myStyle' = the user's personal tone. 'creators' = a chosen creator's style. Do not use remix.
`number_of_posts`	No	Number of posts to generate (5-20). Defaults to 10.
`user_instructions`	No	Optional free-form instructions to guide the AI generation. Example: 'Focus on practical startup lessons' or 'Keep tone punchy and contrarian'.

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.3/5.0

Behavior5/5

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

Annotations only declare a coarse safety profile (readOnlyHint=false, idempotentHint=false, destructiveHint=false). The description adds the operationally critical facts the annotations cannot convey: the tool is asynchronous, returns a job_id immediately, takes 1–3 minutes, and requires polling of a named sibling tool. It also tells the agent what to say to the user while waiting.

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?

The critical constraint (async job, must poll) is well front-loaded, but the polling instruction is repeated almost verbatim in the first and second paragraphs, and the 'do not offer deprecated options' warning appears in both the prose and the deprecated-option notes for two separate parameters. Duplication costs space in a description that is already long.

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?

There is no output schema, and the description compensates fully by explaining exactly what the call returns (job_id), what the agent must do with it, and how long the operation runs. For an async, multi-step, user-facing generation tool, nothing an agent needs in order to invoke it correctly is missing.

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 every parameter is already documented in structured data, and the description's numbered list largely mirrors those same descriptions rather than adding new detail. The conditional rule ('creators required when ideaSource is creator OR writingStyle is creators') is valuable but is also restated in the creators field description, so the marginal gain is small.

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

Purpose4/5

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

States a specific verb and resource ('Generate new X/Twitter post ideas using the current Ideas Lab engine') and immediately clarifies the return shape — a job_id, not posts. It does not, however, differentiate itself from the sibling 'generate_ideas_from_posts', which an agent could easily confuse with this one given the nearly identical naming.

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?

Explicitly states the workflow prerequisite (collect all required answers from the user before calling, no defaults), the mandatory follow-up (call check_ideas_status with the returned job_id until completed/failed), and the exclusions ('Do NOT offer deprecated options: remix, niche, viral, or myPosts'). The 'do not stop after 30 seconds' note pre-empts a very specific failure mode.

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

All SupaBird tools Inspect

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

Need Help?