Skip to main content
Glama

send_share_link

Email an existing share's link from the account's branded sender. For a file still to be uploaded, prefer notify_email on create_upload_handoff: the uploader's browser sends the link and you never see the key. Use this only when the human volunteered the full link (with #key) unprompted, which transits the mail server once and is never stored, or with strict=true to send a keyless link for a password-protected share.

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": {
      "share_id": "<share_id>",
      "to": "<to>"
    },
    "name": "send_share_link"
  }
}

Input Schema

NameRequiredDescriptionDefault
toYesUp to 10 recipient email addresses.
linkNoThe FULL share link including the #key fragment, if the human gave it to you. Omit for strict mode.
strictNoSend the link without its key; the share must be password-protected and the recipient gets the password separately.
messageNo
share_idYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Annotations only declare it is a non-destructive, non-idempotent, open-world write; the description adds the substantive behavior: the full key transits the mail server once and is never stored, and strict mode requires a password-protected share with the password delivered separately. That is exactly the security-relevant context an agent cannot infer from the schema or hints.

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?

Three dense sentences, front-loaded with the core action before the alternative and the key-handling caveats. Slightly heavy in subordinate clauses ("which transits the mail server once and is never stored"), but 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?

For a send-side tool with no output schema, it covers purpose, preconditions, sibling routing, and key exposure behavior. Missing only outcome/error expectations (e.g., what a failed send looks like) and mention of the message parameter.

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 60%, and the description explains the two ambiguous parameters well: link must be the FULL link including #key, and strict sends keyless with a password-protected precondition. It says nothing about message or share_id, leaving part of the gap unfilled.

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?

States a specific verb and resource (email an existing share's link) plus who sends it (the account's branded sender), which immediately separates it from generic notification tools. The opening clause alone lets an agent distinguish it from create_upload_handoff or send_request.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly names the alternative (notify_email on create_upload_handoff) for files not yet uploaded and explains why. It further narrows the trigger to two cases: the human volunteered a full link with #key unprompted, or strict=true for a password-protected share.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources