Skip to main content
Glama

Edit a Pulse article's brief

flypost_update_article_brief
Idempotent

Adjust an article's brief before it is written — the app's Brief screen. Drop or restore sources, switch research mode, and reorder outline sections. Read the current brief (ids included) from flypost_get_article or the result of flypost_prepare_article / flypost_outline_article. Source and research-mode changes apply on the next outline rebuild: run flypost_outline_article after this, as the app's "Update brief" does. Section order applies to the next flypost_generate_article. To add a NEW Brain source, use add_source_ids on flypost_outline_article instead. article_type switches the format (guide / list / roundup); an outline built for the old type no longer fits, so run flypost_outline_article after changing it.

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_update_article_brief"
  }
}

Input Schema

NameRequiredDescriptionDefault
article_idYes
article_typeNoSwitch the format: guide (how/why sections), list (numbered points) or roundup ("best X", each entry researched first). Rebuild with flypost_outline_article afterwards.
research_modeNo'source' = the user's own Brain; 'web' = live web research. Applies on the next outline rebuild.
section_orderNoEvery outline section id, in the new order (e.g. ["section_3","section_1","section_2"]).
exclude_source_idsNoBrief source ids to leave out of the article (the writer skips unselected sources).
include_source_idsNoBrief source ids to bring back in.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only declare the mutation is non-destructive and idempotent; the description adds the far more important trait that effects are deferred and staged — source and research-mode changes land on the next outline rebuild, section order lands on the next flypost_generate_article. It also discloses a real hazard the annotations cannot: changing article_type invalidates an existing outline because 'an outline built for the old type no longer fits.' That is meaningful behavioral context beyond structured fields.

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 purpose, then constraint/alternative details, with no filler sentences. Minor deduction: the instruction to run flypost_outline_article afterward is repeated three times (after general changes, after the

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 six-parameter mutation tool with no output schema, the description covers everything an agent needs: where to read current ids, what each change affects, the required follow-up call, the format-switch hazard, and the sibling to use for a different goal. Nothing material is left to inference.

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 83%, so the baseline is 3; the description earns an extra point by adding temporal meaning the schema does not carry — which parameters take effect on the next outline rebuild versus the next generate call, and the consequence of switching article_type. The add-a-new-source distinction (include_source_ids restores existing brief sources only, add_source_ids creates new ones) is a genuinely useful disambiguation beyond the field text.

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 opening clause gives a specific verb and resource ('Adjust an article's brief') and immediately scopes the timing ('before it is written') plus the UI anchor ('the app's Brief screen'). It enumerates the concrete operations (drop/restore sources, switch research mode, reorder outline sections), so the agent can tell it apart from flypost_outline_article and flypost_update_draft without reading 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?

Explicitly names prerequisites (read the current brief with ids from flypost_get_article or the result of flypost_prepare_article / flypost_outline_article) and the required follow-up ('run flypost_outline_article after this'). It also names a hard exclusion with a redirect: adding a NEW Brain source must go through add_source_ids on flypost_outline_article instead. This is exactly the when/when-not/alternative pattern.

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.