Skip to main content
Glama

webex_save_file

Download a Webex message attachment to local disk (up to 100 MB) and return its saved path for local readers.

Instructions

Save attachment to local disk (max 100 MB); returns path for local readers. Directory: WEBEX_DOWNLOAD_DIR or ~/.cache/webex-mcp/downloads//. Overwrites existing file; never execute untrusted downloads.

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": {
      "fileUrl": "<fileUrl>"
    },
    "name": "webex_save_file"
  }
}

Input Schema

NameRequiredDescriptionDefault
fileUrlYesMessage files[] contents URL

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.0

TDQS

B3.3/5.0
Behavior2/5

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

No annotations exist, so the description carries the entire behavioral burden; it does disclose the 100 MB ceiling, the exact destination directory template, the overwrite-on-existence behavior, and a security warning. It omits what happens when the file exceeds 100 MB (error vs truncation), whether authorization comes from the URL or from the caller's credentials, and how partial or failed writes are handled.

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 dense, semicolon-delimited single paragraph front-loads what the tool does, then size, then destination, then risk. Every clause carries information, though the telegraphic phrasing is slightly harder to parse than plain sentences.

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 one-parameter local-write tool with no output schema, the description covers the practical essentials: destination path resolution, overwrite semantics, size limit, and the returned path. The main remaining gap is failure behavior at the size boundary and where the download credentials come from.

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?

With a single parameter at 100% schema coverage the schema already explains fileUrl as the "Message files[] contents URL", and the description adds nothing about URL form, expiry, or authentication. The path template incidentally clarifies that a message uuid is derivable from the URL, which is mild added meaning.

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?

"Save attachment to local disk" states a concrete verb and resource, and the size cap and returned path sharpen it. It does not distinguish itself from its close siblings webex_download_file and webex_save_message_files, so an agent must infer the boundary rather than read it.

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?

"returns path for local readers" implicitly signals when to prefer this over a streaming download, and "never execute untrusted downloads" is a safety caveat rather than a usage rule. There is no explicit when-to-use guidance and no named alternative among the sibling file tools.

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