Skip to main content
Glama

add_interaction

Append event-and-action interactions to Axure RP widgets or pages, with optional event replacement, on-page targeting, and conditional JSON case support.

Instructions

向元件或页面追加事件+动作交互(支持 --replace-event、--on-page、--json 条件/多 Case;FCall 函数名按 18 项注册表白名单校验)。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 gui-roundtrip,只适用 capabilities.md 的已验样本。CLI: node add-interaction.mjs source.rp output.rp <widgetName|pageName> [--page] [--on-page ] [--replace-event] --event --action [key=value ...]

Input Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.4.5

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare that this is a non-read-only, non-destructive, closed-world mutation. The description adds real behavior beyond that: FCall function names are validated against an 18-item registry whitelist, --replace-event replaces rather than appends, and the tool is only verified for samples registered in capabilities.md via gui-roundtrip. It does not say what happens on whitelist rejection or what is returned.

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 purpose is front-loaded, but the description is dense with parenthetical asides and ends with a full CLI synopsis that largely restates the input schema. The evidence-registration sentence ('登记证据 gui-roundtrip,只适用 capabilities.md 的已验样本') is cryptic and could be tightened.

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 a tool with two mutually exclusive call modes (named parameters vs raw args) and a chain/session model, the description covers both modes, the whitelist constraint, and the replace semantics. No output schema exists, yet the description says nothing about return values or failure modes, which is the main remaining gap.

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 baseline is 3; the description goes further by explaining the session:true contract (source/output omitted and injected from the chain) and by describing the --replace-event and --on-page behaviors and the key=value tail form. It still leaves the exact parameter vocabulary for the action types to the CLI synopsis rather than explaining it.

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 first clause states a precise verb and resource: '向元件或页面追加事件+动作交互' (append an event+action interaction to a widget or page). The additive verb 'append' also implicitly contrasts with the sibling remove_interaction, and the scope (widget or page, via --page/--on-page) is stated up front.

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 concrete usage rules: named invocation omits host source/output and uses the session chain; raw args require session:true and must also omit those two parameters, except multi-source tools which keep the import source. It also warns that explicit paths do not advance the chain. What is missing is guidance on when to choose this tool over add_click_link or remove_interaction, but the invocation-mode guidance is clear and specific.

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