Skip to main content
Glama

Prepare a Pulse article brief (server pipeline)

flypost_prepare_article

Step 1 of Flypost's own long-form writer (server-side AI + web research). Prefer flypost_save_article when you can write the article yourself — it is faster and costs the user nothing. Use this when the user explicitly asks for Flypost to write it, or wants its built-in research. Creates the article from topic + target_query + angle (or takes an existing article_id) and gathers Brain material into a brief. Then build the outline with flypost_outline_article. Always set target_query: it steers the writer and is what keyword tracking reports on. Set article_type to match the query (list for numbered points, roundup for "best X" lists); when you leave it out the result carries suggested_article_type if Flypost would pick another one. To write from research you gathered (or the user collected), save it to a notebook first and pass notebook_id.

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": "flypost_prepare_article"
  }
}

Input Schema

NameRequiredDescriptionDefault
angleNo
topicNoTopic for a new article when article_id is omitted.
article_idNo
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.
article_typeNoThe article format. guide (default): explains how or why in 4-7 sections ("how to measure share of voice"). list: numbered points, one per H2, count taken from the brief ("10 questions to ask an agency", "a 25-point checklist"). roundup: "best X for Y" written by the author in the first person as having tested the tools ("I tested 8 Taplio alternatives: here are the best"), one H2 per entry with the same sub-structure, a how-I-chose section, a comparison and an FAQ; every entry is researched first (from the notebook when notebook_id is set, else one web search per entry) and only sourced facts are used, so it takes longer. Match it to target_query. Omitted on a new article = guide.
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.

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?

Beyond the annotations (readOnlyHint false, openWorldHint true), it discloses the material costs the agent must weigh: server-side AI spend, roundups taking longer because every entry is researched first, and 'a tool the notebook does not cover is left out' under research_mode source. It also states that the call creates the article and gathers Brain material into a brief, so the side effect is clear despite the non-destructive annotation.

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 content is dense but front-loaded with the step identity and the sibling alternative, and most sentences carry operational weight. A few clauses repeat what the enum and property descriptions already say, so the definition is longer than strictly necessary without being padded.

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 an 8-parameter, all-optional tool with no output schema, the description covers sequencing, defaults, the source/notebook workflow, and the one return cue that matters (suggested_article_type when article_type is omitted). What the returned brief actually contains is left implicit, which is a minor gap given there is no output schema.

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 75% and the schema text is already detailed, but the description adds cross-parameter guidance the schema does not: always set target_query because it steers retrieval and drives keyword tracking, set article_type to match the query, and treat notebook_id and research_mode together (source keeps roundups inside the notebook, online fills in live pricing). Some of the article_type and research_mode explanation restates the enum documentation, which keeps this below a 5.

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 by naming the exact operation and its place in the pipeline ('Step 1 of Flypost's own long-form writer (server-side AI + web research)'), and states the two input modes (topic + target_query + angle, or an existing article_id). It distinguishes itself from flypost_save_article and flypost_outline_article by name and by role.

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 an explicit routing rule: prefer flypost_save_article when the agent can write the article itself because that is faster and free, and use this only when the user explicitly asks Flypost to write it or wants its built-in research. It also names the required next step (flypost_outline_article), the prerequisite for researched material (save to a notebook first), and conditional rules for research_mode and roundup sourcing.

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.