Skip to main content
Glama

brochure_draft

Idempotent

Draft the public page (a cubicle.brand.md brochure) of something you own: your listed agent's desk, your own strategy once the reader gate graded it PROVEN (its gate id tenant-), your own kept indicator script (my:), or for the house a measured strategy, a shared vault or a chart indicator. The page's numbers (the record at taker costs, the reader gate's verdict, the null p, the house windows, the day grid, the equity line, the venues, the fingerprint and receipts) are read from the subject's data on every visit and never typed; a model writes the prose only, checked for figures, claims of profit, reserved names and other organisations' names. Returns the slug, the public path, the file and anything to fix. Calling it again for the same subject returns the same draft. Then brochure_publish.

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": {
      "kind": "<kind>",
      "subject": "<subject>"
    },
    "name": "brochure_draft"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindYeswhat the page is about
slugNooptional: the page's address, 3 to 48 of a-z 0-9 -; made from the title when left out
modelNooptional: false drafts the prose from the subject's facts alone, with no model (for an agent that writes its own prose next)
titleNooptional: the page's title (at most 60 characters)
subjectYesagent: your desk's attribution or its board id (it must be listed on the board first: agent_list); strategy: your strategy's reader gate id tenant-<entry> once graded PROVEN, or for the house a measured strategy's id; vault: a shared vault's id; indicator: a chart indicator's id or my:<your kept script>

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / subject / description
      Previous value: -"agent: your desk's attribution or its board id (it must be listed on the board first: agent_list); strategy: a measured strategy's id; vault: a shared vault's id; indicator: a chart indicator's id or my:<your kept script>"New value: +"agent: your desk's attribution or its board id (it must be listed on the board first: agent_list); strategy: your strategy's reader gate id tenant-<entry> once graded PROVEN, or for the house a measured strategy's id; vault: a shared vault's id; indicator: a chart indicator's id or my:<your kept script>"
  2. Added

TDQS

A3.6/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false, idempotentHint=true, destructiveHint=false, and the description is consistent with all three. Beyond that it discloses real behavior: page numbers are read from the subject's live data and never typed, the model writes prose only, the output is checked for figures, profit claims and other organisations' names, and a repeat call is a no-op returning the same draft. Missing are any permission or ownership-enforcement details and any indication of how long a draft persists before publish.

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

Conciseness3/5

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

The key actions (draft, read-from-data, checked, returns, idempotent, then publish) are front-loaded correctly and no sentence is purely decorative. However, the middle sentence is a long parenthetical pile-up of nouns ("the record at taker costs, the reader gate's verdict, the null p, the house windows, the day grid, the equity line, the venues, the fingerprint and receipts") that costs more attention than the information value it returns.

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?

With five parameters, no output schema and a non-trivial write action, the description does the work: it names the returned values (slug, public path, file, anything to fix) and explains the idempotency contract. Eligibility and sequencing are covered between description and schema. Only the draft's lifecycle before publish is left implicit.

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 100%, so the schema already documents kind, slug, model, title and subject with their formats and enumeration. The description restates the subject mapping and adds the eligibility condition "once the reader gate graded it PROVEN", but provides no format syntax or defaults beyond what the schema supplies. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource: "Draft the public page (a cubicle.brand.md brochure) of something you own", then enumerates the four subject kinds it covers. It is distinguishable from siblings like brochure_publish by the explicit handoff sentence. Clarity is dented only by undefined house jargon ("reader gate", "house", "kept indicator script"), which makes the sentence harder to parse than the underlying purpose warrants.

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

Usage Guidelines3/5

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

It gives sequencing guidance ("Then brochure_publish") and states that repeat calls for the same subject return the same draft, which is genuinely useful. Prerequisites for eligible subjects live in the schema (agent must be listed on the board, strategy must be graded PROVEN) rather than the description. It never says when not to use it, nor how it relates to the sibling brochure_update, which is the most likely confusion point.

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