Skip to main content
Glama

axure_save

Save the current chain tail to a new whitelisted deliverable file with overwrite protection and return its absolute path and SHA-256; omit the target name to inspect current tail status.

Instructions

链尾另存为交付文件(白名单+防覆盖,只写新文件),返回绝对路径与 SHA-256;省略 as 时返回链尾现状(路径/SHA/三零)。

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": "axure_save"
  }
}

Input Schema

NameRequiredDescriptionDefault
asNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.4.5

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=false, and the description reinforces this with substantive detail: a path whitelist, overwrite protection, and the guarantee that only new files are written. That is exactly the kind of context annotations cannot carry. It loses a point for not saying what happens when 'as' targets a non-whitelisted directory or an existing file — error, rejection, or fallback rename.

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?

One dense sentence with the write behavior and the dual-mode result front-loaded, and no redundant restatement of the tool name. The parenthetical stacks several constraints and the terminal '三零' is opaque enough to cost readability.

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?

With one parameter and no output schema, the description must cover return shape and constraints — it names the path/SHA-256 return but leaves '三零' undefined and never states which directories the whitelist permits, which an agent needs before calling a file-writing tool. Adequate but with a real operational 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 0% and the single parameter 'as' is documented only as a non-empty string, so the description carries the load — and it does, explaining that supplying 'as' triggers save-as while omitting it switches the tool to a status read. What it does not specify is whether 'as' is a full path, a filename, or a path relative to the whitelist root.

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 gives a specific verb (save-as) and a concrete output artifact (a delivery file), plus the return payload (absolute path and SHA-256), so the agent knows this is a write-to-disk tool. It stops short of a 5 because '链尾' (chain end) and '三零' are project jargon that is never defined, and no sibling is named to contrast against axure_state, which likely also exposes state.

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 implicitly defines two modes: supply 'as' to write a new file, omit it to read the current chain-end status. That is useful mode guidance, but there is no explicit when-to-use versus when-not, no warning that omitting 'as' turns this into a read operation, and no pointer to axure_state as an alternative for state queries.

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