Skip to main content
Glama

read_interactions

Read-only

Reads complete event, case, and action trees with pagination and page/widget filters, including nested widgets and masters, to inspect interactions in Axure RP prototypes.

Instructions

读取完整事件/Case/动作树。分页以统一 items 为准,包含页面事件、顶层元件、嵌套元件和母版;offset 是跳过的拥有者数,returned 是本次条数。contained 仅为嵌套元件的兼容视图,为空不代表本页没有交互。默认 limit=20,响应接近 20KB 时减少条数,按 nextOffset 继续;支持 page/widget(逻辑 ID、原生名称或对象 ID)过滤,可传 path/rp/file 只读查看 .rp。

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "read_interactions"
  }
}

Input Schema

NameRequiredDescriptionDefault
rpNo
fileNo
pageNo
pathNo
limitNo最多读取的交互拥有者数量;响应预算可能减少本次 returned。
offsetNo从统一 items 顺序跳过的拥有者数量,默认 0;继续使用 nextOffset。
rpFileNo
widgetNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.4.5

TDQS

A4/5.0
Behavior5/5

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

Beyond the readOnlyHint annotations, the description explains pagination mechanics in detail: offset counts owners skipped, returned is this batch's count, nextOffset continues, and the default is limit=20. It also discloses the ~20KB response budget that can reduce returned, and the 'contained' compatibility caveat that an empty value does not mean no interactions. These are non-obvious behaviors an agent needs in order to call and interpret the tool correctly.

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 pagination and budget rules come first, followed by the filter options, and every sentence carries actionable content. The prose is dense and clause-chained, which slightly hurts readability, but there is no filler.

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?

Given no output schema, the description does well by explaining response fields such as unified items, returned, nextOffset, and contained. For an 8-parameter, paginated read tool, this is nearly complete; only the overlapping rp/rpFile/file inputs remain undefined.

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?

With only 25% schema coverage and 8 parameters, the description contributes real meaning: it explains offset/limit semantics and nextOffset continuation, and says page/widget accept a logical ID, native name, or object ID. It also notes that path/rp/file switch to read-only .rp viewing. The distinction between the rp, rpFile, and file parameters is left ambiguous, which is the main gap.

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: it reads the full event/Case/action tree. It also scopes the read (page events, top-level widgets, nested widgets, masters), so an agent can tell what it returns. It does not name a sibling such as inspect or diagnose_prototype, so the boundary is inferred rather than stated.

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 implies usage through filter options (page/widget) and the read-only path/rp/file mode, so an agent can infer that this tool is for paged inspection of a .rp file. It never explicitly says when to prefer it over the inspection or diagnose siblings, and no exclusions are given.

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