Skip to main content
Glama

Build or rebuild a Pulse article's outline

flypost_outline_article
Destructive

Step 2 of the staged article flow: build the outline from the prepared brief, or rebuild it. Returns the brief; show it to the user when they want a say, and adjust it with flypost_update_article_brief (drop weak sources, switch research mode, reorder sections). After changing sources run this again to rebuild, optionally with feedback and add_source_ids. A rebuild replaces the current outline. Then write the body with flypost_generate_article. Pass notebook_id to rebuild it from a different notebook.

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": {
      "article_id": "<article_id>"
    },
    "name": "flypost_outline_article"
  }
}

Input Schema

NameRequiredDescriptionDefault
feedbackNoWhat to change about the brief.
article_idYes
project_idNoProject id; omit for the active project.
notebook_idNoWrite from ONE notebook: the brief, outline and article retrieve only from its sources. Pass the source_package_id that flypost_create_notebook returns (or a notebook id from flypost_list_sources). Typical flow when you did the research yourself: flypost_create_notebook, then save each finding with flypost_add_source_url or flypost_add_source_text (one source per tool or page you researched), then flypost_prepare_article with notebook_id and research_mode "source". For a roundup, everything comes from the notebook: save a source per tool (your own company and, for "X alternatives", X itself included), with the tool named in its title or saved from its own site so it can be matched. With research_mode "source" a tool the notebook does not cover is left out. Set on a new article, or moves an existing one onto that notebook.
target_queryNoThe exact search query the article is trying to rank for, e.g. "what is an impression on linkedin". Steers the writer's retrieval and prompts, and is the keyword the app's rankings report tracks. Sets it on a new article, or updates it on an existing one.
research_modeNosource: ground only on the Brain (or on notebook_id when given). online: also research the web. With notebook_id, source keeps the article to that notebook with no web search at all; online adds fresh web stats and, for a roundup, web research for whatever the notebook does not cover (entries, the tool being replaced). A roundup with no notebook should use online: its entries need live pricing and features.
add_source_idsNoREAL Brain source item ids (from flypost_search_source_docs) to pull into the brief and force-load — the app's "Add from Brain".

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 already flag destructiveHint=true and openWorldHint=true, and the description earns credit by concretizing the destruction: 'A rebuild replaces the current outline.' It also discloses that the tool returns the brief and that the brief should be shown to the user, which the annotations cannot convey.

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 step and core action, then ordered into review, rebuild, write, and notebook-variant cases. Dense but nearly every clause carries operational meaning; the parenthetical example list is the only mildly expendable element.

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?

For a 7-parameter, destructive, multi-stage tool with no output schema, the description covers sequencing, what the call returns, and what gets overwritten. The only gap is what the produced outline actually looks like, which is minor since the brief is returned for inspection.

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 86%, so the baseline is 3; the description adds real semantics by explaining feedback and add_source_ids are supplied on a rebuild and by scoping notebook_id to 'rebuild it from a different notebook' — a use case the schema frames only as setting/moving an article. It does not restate the enum behavior for research_mode, which the schema already handles.

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 ('build the outline', 'rebuild it') and anchors it in the staged flow as step 2, so the agent knows exactly where it sits relative to flypost_prepare_article and flypost_generate_article. Sibling tools are named explicitly rather than left to inference.

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 when-to-use ('after changing sources run this again'), the follow-on tool (flypost_generate_article), and the correct alternative when the user wants edits (flypost_update_article_brief with concrete examples: drop weak sources, switch research mode, reorder sections). It also states the notebook_id rebuild case.

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.