Skip to main content
Glama

Write a draft from a brief

create_draft

Writes a publishable first draft in Hi, Moose from a content brief, in the brand's voice, grounded in the brief, Brand Truth and brand guidelines, with internal links chosen from the brand's own site crawl and a polish pass. Pass the briefId returned by create_content_brief, or a brief written elsewhere as markdown. Takes one to three minutes. Returns the draft as markdown plus a draftId for create_featured_image. Give the draft to the user in full. Every line of guidance is treated as a requirement and outranks the brief and the Brand Truth wording where they differ. Hi, Moose checks the finished draft against every line, fixes what is missing, and returns guidanceCheck on every draft, listing each requirement as met or not met. When guidanceCheck lists unmet requirements, or says the check did not run, tell the user.

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": {
      "project": "<project>"
    },
    "name": "create_draft"
  }
}

Input Schema

NameRequiredDescriptionDefault
briefNoA brief written elsewhere, as markdown. Use this instead of briefId when the brief did not come from Hi, Moose. Up to 60000 characters.
briefIdNoThe briefId returned by create_content_brief. Use this when the brief came from Hi, Moose.
projectYesThe Hi, Moose project, by its name as shown by list_projects. The projectId is also accepted.
guidanceNoOptional: requirements for the draft, one per line. Every line is a hard requirement. Write each URL the draft must link to in full, give each statistic with its source, and paste any text that must appear word for word (a legal disclaimer, a quote). A URL written here is used exactly and is never replaced by a page from the site crawl. A figure written here is used exactly, and a line that rules out a phrase or an example applies to the whole draft, even when the Brand Truth uses it. Up to 20000 characters.
briefTitleNoOptional: the working title, when passing a brief as markdown.
templateTypeNoOptional: the kind of content, for example "Blog post", "Landing page", "Guide". Used when passing a brief as markdown.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / guidance / description
      Previous value: -"Optional: requirements for the draft, one per line. Every line is a hard requirement. Write each URL the draft must link to in full, give each statistic with its source, and paste any text that must appear word for word (a legal disclaimer, a quote). A URL written here is used exactly and is never replaced by a page from the site crawl. Up to 20000 characters."New value: +"Optional: requirements for the draft, one per line. Every line is a hard requirement. Write each URL the draft must link to in full, give each statistic with its source, and paste any text that must appear word for word (a legal disclaimer, a quote). A URL written here is used exactly and is never replaced by a page from the site crawl. A figure written here is used exactly, and a line that rules out a phrase or an example applies to the whole draft, even when the Brand Truth uses it. Up to 20000 characters."
  2. Changed2 schema fields changed
    • changedInput schema / properties / guidance / description
      Previous value: -"Optional: extra requirements for the draft (angle, must-include points, tone). Up to 4000 characters."New value: +"Optional: requirements for the draft, one per line. Every line is a hard requirement. Write each URL the draft must link to in full, give each statistic with its source, and paste any text that must appear word for word (a legal disclaimer, a quote). A URL written here is used exactly and is never replaced by a page from the site crawl. Up to 20000 characters."
    • changedInput schema / properties / guidance / maxLength
      Previous value: -4000New value: +20000
  3. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Beyond the annotations, the description discloses runtime behavior: one to three minutes, returns markdown plus draftId, treats every guidance line as a hard requirement outranking the brief and Brand Truth, performs a guidance check, and returns guidanceCheck on every draft. It also states what to tell the user when requirements are unmet or the check did not run. The write behavior is consistent with readOnlyHint=false and destructiveHint=false.

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 definition is front-loaded with what the tool produces and how to invoke it, then covers timing, return values, guidance precedence, and reporting obligations. It is dense but mostly earns its length, though the guidance-check reporting is stated across several sentences and could be tightened.

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?

There is no output schema, so the description carries the return-value burden, and it does so by explaining markdown output, draftId, timing, and guidanceCheck. It also covers the important behavioral edge case of unmet requirements, which is complete enough for this complex generation tool.

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. The description still adds operational meaning beyond the schema: brief versus briefId selection, exact URL and statistic handling, whole-draft scope for exclusions, and the draftId output used by create_featured_image. It does not add much about the required project parameter, leaving that to 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?

The description names a specific verb and resource: writes a publishable first draft in Hi, Moose from a content brief. It clarifies scope with brand voice, Brand Truth, site-crawl link selection, and a polish pass, and distinguishes the two input routes from create_content_brief.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives clear input-routing guidance: pass briefId from create_content_brief or a markdown brief written elsewhere. It also says to give the draft to the user in full, use the returned draftId with create_featured_image, and report unmet guidanceCheck requirements. It does not name when not to use this tool versus alternatives such as refresh_content, so it falls short of fully explicit exclusion guidance.

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.

Resources