Skip to main content
Glama

Save an idea (agent-authored)

flypost_save_idea

Save a post idea you authored yourself into the content bank. Use flypost_get_brand_kit + flypost_search_brain first so the idea fits the brand and its material. The idea can then be developed with flypost_develop_concept. Any material you pass in angle/development_notes is automatically filed into a per-agent Brain source package ('<agent_name> — agent-provided material'), so it stays visible, searchable and covered by claim verification. Put the research you did (what happened, sources, dates, how to frame it) in development_notes: develop uses those notes as this idea's own research, ahead of anything else in the Brain — pass agent_name so it is filed under your name. This tool refuses ideas that duplicate an existing idea, the argument already made in one of its drafts, or a post the user has already published; run flypost_check_coverage on your candidates first so you find that out before you write them, not after.

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": {
      "title": "<title>",
      "target_format": "<target_format>"
    },
    "name": "flypost_save_idea"
  }
}

Input Schema

NameRequiredDescriptionDefault
angleNoThe idea card description: 1-2 reader-facing sentences describing the idea, exactly as it should appear under the title. Write it as a description of the post, NOT as instructions to the AI ('Open with...', 'Carousel walks...' belong in development_notes).
titleYesThe idea card headline. Match the format of native brainstormed ideas: a short, punchy, plain headline (max 90 chars, no quotes, no em dashes, no appended explainer clause).
agent_nameNoYour product name as the calling agent (e.g. 'Claude'). Names the per-agent Brain source package your material is filed into and the 'Idea by …' attribution shown in the post editor. Defaults to 'AI agent'.
project_idNoProject id; omit for the active project.
target_formatYesThe post format the idea targets.
authoring_noteNoOne short sentence on what this is based on (e.g. the conversation or document it came from). Shown as attribution in the post editor.
development_notesNoPrivate guidance for the develop step — required openers, verbatim quotes, structure. Stored with the concept seed and used during development; never shown on the idea card.
source_package_idNoOptional notebook to ground development on.
acknowledge_duplicateNoSave even though this collides with an existing idea or an already-published post. Only pass this when the user has decided to revisit the topic deliberately — never to get past the refusal on your own judgement.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Annotations only declare non-read-only, non-destructive, closed-world; the description adds substantially more: automatic filing of angle/development_notes into a per-agent Brain source package covered by claim verification, precedence of development_notes as the idea's own research, and a duplicate refusal that applies to existing ideas, draft arguments, and already-published posts. The acknowledge_duplicate caveat ('never to get past the refusal on your own judgement') is exactly the kind of behavioral constraint annotations cannot carry.

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 core action, then prerequisites, then mechanics, then the refusal rule — a sensible order. It is dense and slightly repetitive (the Brain filing is described twice across two sentences), but nearly every clause carries operational information rather than filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With nine parameters, no output schema, and thin annotations, the description does the heavy lifting on side effects, ordering, and failure modes. The only real gap is that it never indicates what the agent gets back (e.g. an idea id for later develop/discard calls), which matters for a tool whose output feeds a multi-step pipeline.

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 beyond the schema for development_notes (used as the idea's own research, ranked ahead of the rest of the Brain, never shown on the card) and agent_name (names the filing package and the attribution). It does not add anything for project_id, target_format, or source_package_id, but those are self-explanatory in the schema.

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 a post idea ... into the content bank') and immediately scopes it with 'you authored yourself', which separates it from the sibling brainstorm generator. An agent can tell this is the write path for self-generated ideas 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 an explicit pre-flight sequence (flypost_get_brand_kit + flypost_search_brain, then flypost_check_coverage on candidates before writing) and names the downstream tool (flypost_develop_concept). It also states the refusal conditions and the deliberate-override path, so when-to-use and when-not-to-use are both covered.

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.