Skip to main content
Glama

create_blank_project

Generates a single-page blank Axure RP 9 or 11 project by copying the matching native blank template from your machine, so you can start an editable prototype without manual setup.

Instructions

复制用户本机的 RP 9 / RP 11 原生空白模板生成单页空白 .rp 工程(模板按目标版本绑定)。具名调用省略宿主源/输出即使用会话链;原始 args 用 session:true 并省略这两个参数(多源工具保留导入源)。显式路径不推进链。 登记证据 loaded,只适用 capabilities.md 的已验样本。CLI: node create-blank-project.mjs <output.rp> [--version 9|11]

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": {
      "args": "<args>"
    },
    "name": "create_blank_project"
  }
}

Input Schema

NameRequiredDescriptionDefault
argsYes
sessionNotrue 时 args 省略宿主源和输出,由当前链注入;多源工具仍传导入源。

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.4.5

TDQS

A3.5/5.0
Behavior4/5

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

Annotations only declare non-read-only, closed-world, non-destructive. The description adds meaningful behavior beyond that: it copies a local template, the template is version-bound, session-chain advancement is conditional on whether explicit paths are given, and evidence registration ('loaded') is limited to verified samples. Those are non-obvious side effects the annotations cannot convey, though the evidence/'capabilities.md' clause is left opaque.

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?

Front-loads the purpose correctly and the CLI line is a concrete, useful anchor, but the middle passage is dense with internal shorthand ('宿主源', '会话链', '登记证据 loaded') and references an external file, so it reads as compressed rather than concise.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, and the description does not say what is returned or how failure (missing template for a version, unverified sample) surfaces. For a file-producing tool with a cryptic free-form args array, more should be spelled out, though the version-binding and session-chain rules cover the main decision points.

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 coverage is 50%; the 'session' param is documented in the schema, while 'args' has no schema description. The description partly compensates by explaining that with session:true, args omits host-source and output, and the CLI line implies args carries the output path plus a --version 9|11 flag. That is useful but indirect and leaves the args ordering/format ambiguous.

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 first sentence names a specific action and artifact: copy the local RP 9/RP 11 native blank template to produce a single-page blank .rp project, with the template bound to the target version. That distinguishes it from sibling create_blank_page (a page, not a project), though it never names siblings explicitly.

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 conditional guidance: named invocation omitting host-source/output uses the session chain, raw args use session:true and omit those params, explicit paths do not advance the chain, and multi-source tools keep the import source. This is real when-to-use routing, but it is written in internal jargon and defers validity to an external capabilities.md rather than stating conditions directly.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools