Skip to main content
Glama

save_idea

Save one or more ideas to the Ideas tab of the active workspace: thoughts that are not posts yet. No AI, the text is stored verbatim. Use this, not save_draft, when moving a backlog of ideas in from another tool; call select_workspace first to pick the client they belong to, and list_ideas to skip any already there. All the ideas in one call are saved together, or none are. When the ideas belong to a teammate, pass their name as author so they land on that person's Ideas tab; one author per call, applied to every idea in it. If an idea comes with source material (call notes, a transcript, an article, a link), put it in that idea's references, NEVER in content: the idea's text is what gets drafted into the post, references are stored alongside it and carried over to the post when the idea is drafted. Each idea can carry tags by name, the same workspace tags posts use; they go with it when it is drafted.

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": {
      "ideas": "<ideas>"
    },
    "name": "save_idea"
  }
}

Input Schema

NameRequiredDescriptionDefault
ideasYesThe ideas to save, up to 100 per call.
authorNoOptional: whose ideas these are. A teammate's name, or 'me'. Omit to save them as yours. Only people who can see everyone's posts may save as someone else.
workspaceNoOptional: the workspace (client) to answer from for this call only, by name (e.g. 'Acme') or numeric id, as returned by list_workspaces. Leave it out to use the current workspace. It does not change the current workspace; use select_workspace for that.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / workspace
      Added value: +{
      +  "description": "Optional: the workspace (client) to answer from for this call only, by name (e.g. 'Acme') or numeric id, as returned by list_workspaces. Leave it out to use the current workspace. It does not change the current workspace; use select_workspace for that.",
      +  "type": "string"
      +}
  2. First observed

TDQS

A4.9/5.0
Behavior5/5

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

Annotations only say the call is a non-read, non-destructive, open-world write; the description goes well beyond that by disclosing atomicity ('saved together, or none are'), that no AI processing occurs and text is stored verbatim, and that references are carried over to the post at drafting time. It also flags the permission constraint on saving as another person.

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 purpose and the save_draft contrast are front-loaded, and nearly every sentence carries a distinct rule. It is a single dense paragraph, though, and the author/references/tags rules would be easier to scan as separated clauses; no sentence is outright filler.

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 3-parameter bulk-write tool with no output schema, the description covers atomicity, permissions, workspace targeting, author scoping, reference-vs-content separation, and tag matching behavior, which is everything an agent needs to invoke it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline would be 3, but the description adds genuine meaning: author applies to every idea in the call and only one author per call, and references must never be folded into content because content is what gets drafted. That is behavioral guidance the schema alone does not convey.

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 ('Save one or more ideas to the Ideas tab of the active workspace') and immediately disambiguates with 'thoughts that are not posts yet' plus an explicit negative sibling reference to save_draft. An agent can distinguish this from save_draft, list_ideas, and update_idea without opening any schema.

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 routing rules: use this rather than save_draft when bulk-importing a backlog, call select_workspace first to pick the client, and call list_ideas to skip existing entries. It also names the conditions for the optional author path (teammate-owned ideas, one author per call).

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