Skip to main content
Glama
Sign In

SupaBird

by io.supabird.api
OverviewDiscussionsAdmin

Get Saved Ideas

get_saved_ideas
Read-onlyIdempotent

Get the ideas the user saved in SupaBird (My Library → Ideas), newest first.

source:

  • ideas_lab, video_to_posts, rewrite: the user's own generated posts. Each item has id, content, source, saved_at, media_count, and schedulable. To schedule one, call schedule_saved_post with that id (scheduled_date or next_free_slot: true). Templates show schedulable: false; to post a template's text, use schedule_post.

  • content_machine: X posts by other people that the user liked in Content Machine, for inspiration. They come back in content_machine with the author handle, text, url, and metrics, and schedulable: false. Never schedule them as the user's own post. To use one, write an original post from it with write_in_my_style, write_in_supabird_style, or write_like_creator, then schedule that text with schedule_post.

  • all (default): every saved post of the user's own in posts, plus a page of Content Machine items in content_machine.

Drafts the user kept from the composer are listed by get_drafts.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "get_saved_ideas"
  }
}

Input Schema

NameRequiredDescriptionDefault
pageNoPage number, starting at 1. Use pagination.has_next from the previous result to know whether there are more.
limitNoHow many posts to return, 1–50. Defaults to 10.
sourceNoWhich saved ideas to list: 'ideas_lab', 'video_to_posts', 'rewrite' (the user's own posts), 'content_machine' (other people's posts saved for inspiration), or 'all'. Defaults to 'all'.all
social_setNoOnly this social set's items: its name, id or one of its handles. Omit for every set.

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.4/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so safety is covered. Beyond that the description discloses ordering (newest first), per-source return shape (id, content, source, saved_at, media_count, schedulable), the meaning of schedulable: false, the Content Machine fields (author handle, text, url, metrics), and how 'all' is composed. That is substantial added context, though it does not touch pagination limits or error behavior.

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 one-line purpose, then organized into per-source bullets that are easy to scan. Some of the source enumeration restates the schema enum, and the bullet block is long, but nearly every line carries actionable routing information.

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, so the description must describe returns — and it does, per source, including the discriminators (schedulable, media_count, author handle/metrics) an agent needs to act on results. Combined with the scheduling guidance, an agent can call this and proceed without further discovery.

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 genuinely adds meaning beyond the enum labels: it explains what each source value actually returns and precisely how the default 'all' is composed (own posts plus a page of Content Machine items). Page/limit and social_set are left to the schema, which already documents them.

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 ('Get the ideas the user saved in SupaBird'), names the in-app location, and specifies ordering ('newest first'). The per-source breakdown makes clear it is distinct from get_drafts and from the schedule_* tools.

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?

Explicit routing for each result type: call schedule_saved_post with the item `id` to schedule; use schedule_post for template text; for content_machine items write an original post via write_in_my_style/write_in_supabird_style/write_like_creator then schedule_post; drafts live in get_drafts. It also states a prohibition ('Never schedule them as the user's own post'), which is guidance no alternative could convey.

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

All SupaBird 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