Mark

Save Idea

save_idea

Creates, edits, archives or unarchives a content idea. To create: pass title; brief, angleId or pillarId, and buyerQuestionId are optional. To edit: pass id and only the fields that change. To archive or unarchive: pass id and archived: true or false. Archiving never changes the idea's posts. To tie existing posts to an idea: pass id and linkPostIds (from search_posts). It changes only each post's idea, in any status: a post in review, scheduled or published keeps its rev and approval, and a post on another idea moves here. The idea must be active. unlinkPostIds unlinks posts from this idea. One call applies its changes in order (fields, unarchive, unlink, link, archive); a refusal leaves the earlier ones saved, so call list_ideas to check before retrying. To log an idea from a wrong answer: pass wrongAnswerId (from list_wrong_answers); title, brief and buyer question come from it. An angle sets the idea's pillar and persona to the angle's; a pillarId that contradicts the angle is refused. For a pillar on its own, pass angleId null. To draft a post from an idea, call save_post with channel and ideaId. Related: list_ideas, save_post, search_posts, get_brand_context.

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": "save_idea"
  }
}

Input Schema

Name	Required	Description
`id`	No	Existing idea id. Omit to create.
`brief`	No	Optional detail: goal, audience, key points, call to action. null clears it.
`title`	No	What the idea is, in a line. Required to create.
`angleId`	No	Angle id from get_brand_context, or null to clear. Sets the pillar and persona to the angle's.
`archived`	No	With id: true archives the idea, false unarchives it.
`pillarId`	No	Pillar id, or null to clear. With an angle, omit it or pass the angle's own pillar.
`linkPostIds`	No	With id: up to 100 post ids to link to this idea. Only their idea changes.
`unlinkPostIds`	No	With id: up to 100 post ids to unlink from this idea. Posts on another idea are left alone.
`wrongAnswerId`	No	Create only: a wrong answer id from list_wrong_answers. Pass it alone; the title, brief and buyer question come from it.
`buyerQuestionId`	No	One active buyer question id from get_ai_visibility, or null to clear. A website post drafted from the idea answers it.

Output Schema

Name	Required	Description	Default
`idea`	Yes
`appUrl`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedNov 3, 2026

addedInput schema / properties / linkPostIds

Added value: +{
+  "description": "With id: up to 100 post ids to link to this idea. Only their idea changes.",
+  "items": {
+    "maxLength": 64,
+    "minLength": 1,
+    "type": "string"
+  },
+  "maxItems": 100,
+  "minItems": 1,
+  "type": "array"
+}

addedInput schema / properties / unlinkPostIds

Added value: +{
+  "description": "With id: up to 100 post ids to unlink from this idea. Posts on another idea are left alone.",
+  "items": {
+    "maxLength": 64,
+    "minLength": 1,
+    "type": "string"
+  },
+  "maxItems": 100,
+  "minItems": 1,
+  "type": "array"
+}

Changed1 schema field changedOct 29, 2026

addedInput schema / properties / wrongAnswerId

Added value: +{
+  "description": "Create only: a wrong answer id from list_wrong_answers. Pass it alone; the title, brief and buyer question come from it.",
+  "maxLength": 64,
+  "minLength": 1,
+  "type": "string"
+}

AddedOct 14, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Beyond the annotations, it discloses key side effects: archiving never changes posts, linking changes only each post's idea while preserving rev and approval and can move posts from another idea, the idea must be active, and a refusal leaves earlier changes saved so list_ideas should be checked before retrying. These details are valuable for a non-read-only, non-idempotent mutation tool.

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 description is dense but front-loaded, with each operation mode receiving its own sentence and important constraints included. It is appropriately sized for a 10-parameter multi-mode tool, though the packed workflow details could be easier to scan if split more explicitly.

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 a complex multi-mode mutation tool with 10 parameters, annotations, and an output schema, the description covers operation selection, side effects, refusal recovery, cross-tool dependencies, and the follow-on save_post workflow. Nothing critical appears missing.

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 individual parameters are already documented. The description adds meaningful mode-specific semantics: which parameters belong to create versus edit versus archive, where IDs come from (search_posts, list_wrong_answers), and the special rule that a standalone pillar uses angleId null.

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?

The description opens with a specific verb set and resource: creates, edits, archives or unarchives a content idea. It distinguishes this tool from related siblings like list_ideas and save_post by explaining when each applies.

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 explicit per-operation guidance: create with title; edit with id and changed fields; archive/unarchive with id and archived; link posts with linkPostIds; log from a wrong answer with wrongAnswerId. It also routes drafting a post to save_post with channel and ideaId.

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

All Mark 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?