Skip to main content
Glama

patch_link_window

Patches a Page record's link open mode to current or new at byte level, allowing precise correction of link behavior in Axure RP prototypes.

Instructions

字节级改写唯一 Page 记录里链接打开方式 current/new(capabilities.md 未列,仅结构级研究工具)。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 structure,只适用 capabilities.md 的已验样本。CLI: node patch-link-window.mjs <source.rp> <new.rp> <current|new>

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": "patch_link_window"
  }
}

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

B3.4/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false and destructiveHint=false, and 'byte-level rewrite' is consistent with a non-read-only operation. Beyond that, the description usefully discloses chain-advancement semantics and the verified-sample restriction, but it says nothing about failure modes, file/session prerequisites, or whether the original bytes are recoverable.

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 remaining text is a dense run-on of nested parentheticals mixing chain semantics, applicability caveats, and a CLI signature. Each fact is relevant, yet the tangled phrasing forces re-reading to separate invocation modes from constraints.

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?

For a two-parameter mutating tool with no output schema, the description covers invocation modes, chain behavior, and applicability. Gaps remain around what a successful patch yields and what happens when the target sample is not a verified capabilities.md case, which matters given the research-tool framing.

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 only 50% (only session is documented), so the description must compensate, and it does: it explains that session:true injects the host source and output from the current chain, and the CLI line reveals the positional args order (<source.rp> <new.rp> <current|new>) plus the enum-like current/new values for the third argument.

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 states a specific verb and resource: byte-level rewrite of the link open mode (current/new) inside the single Page record. That is concrete enough to distinguish it from generic editing siblings such as patch_string, although the parenthetical 'not listed in capabilities.md, structure-level research tool only' adds jargon that dilutes the core statement.

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 invocation-mode guidance (named calls use the session chain; raw args set session:true and omit host source/output; explicit paths do not advance the chain) and restricts applicability to verified samples in capabilities.md. However, it never says when to pick this over patch_string or add_click_link, so the alternative-selection guidance is only implied.

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