Skip to main content
Glama

Save an article you wrote (agent-authored)

flypost_save_article
Destructive

PREFERRED way to produce a Pulse article: write the article yourself and save it here. Omit article_id to create a new one, or pass it to replace an existing article body. Before writing, read flypost_get_brand_kit + flypost_get_writing_voice and ground claims with flypost_search_source_docs. Body is markdown (## headings, lists, links); the app converts it for the editor. Use flypost_generate_article instead only when the user explicitly wants Flypost's own writer with its built-in web research.

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": {
      "body_markdown": "<body_markdown>"
    },
    "name": "flypost_save_article"
  }
}

Input Schema

NameRequiredDescriptionDefault
angleNo
titleNoArticle title. On update (article_id given) the existing title is kept unless you pass this. On create it defaults to a leading "# " H1 in the body, else topic.
topicNoShort topic label, used when creating a new article.
sourcesNoSources cited in the article, shown in the editor’s sources panel.
article_idNoExisting article to overwrite. Omit to create a new article.
project_idNoProject id; omit for the active project.
target_queryNoThe exact search query the article is trying to rank for. Set it — it is the keyword the app's rankings report tracks. Omitting it on an update leaves the existing keyword alone.
body_markdownYesThe full article body in markdown.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true and readOnlyHint=false, and the description corroborates this by saying article_id "replace[s] an existing article body." It adds context annotations cannot express: that the app converts the markdown into the editor format. It stops short of stating what is overwritten beyond the body or what the call returns.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Four tight sentences, front-loaded with the primary directive and the create/update branch before the optional prerequisites. No filler and nothing repeated from the schema.

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, destructive write tool with no output schema, the description covers the workflow, the overwrite risk, and the format expectations. It does not say what the tool returns on success (e.g., article id) or whether replacement is reversible, which would matter for a destructive operation.

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

Parameters3/5

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

Schema description coverage is 88%, so the baseline is 3; the schema already explains title defaults, target_query, project_id, and sources. The description adds only the create-vs-replace semantics of article_id and the markdown conventions (## headings, lists, links), leaving angle and sources untouched.

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 ("write the article yourself and save it here") and names the sibling it is not (flypost_generate_article). An agent can distinguish agent-authored saving from Flypost's own writer without opening either 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?

Explicit routing rules: this is the PREFERRED path, use flypost_generate_article only when the user wants built-in web research. It also gives prerequisites (read flypost_get_brand_kit and flypost_get_writing_voice first, ground claims with flypost_search_source_docs) and the create-vs-replace condition on article_id.

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.