Skip to main content
Glama

Datasource Sharing Set

datasource_sharing_set
Destructive

Grants viewer or editor access to a reusable datasource for specified people who lack access, with optional invitation emails and dry-run preview.

Instructions

Give people viewer or editor access to a reusable datasource.

members: [{"email": "...", "role": "viewer" | "editor"}], people without access yet; changing or removing an existing member is refused (a person does it in the Share dialog). Runs the datasource's Share dialog as a person does; notify sends Google's invitation email. Google checks each update with reCAPTCHA and may refuse a long automated series (SHARING_REJECTED). Journalled; read back. Use the exact email the user gave or confirmed; never guess an address.

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": {
      "datasource_id": "<datasource_id>",
      "members": "<members>",
      "expected_fingerprint": "<expected_fingerprint>"
    },
    "name": "datasource_sharing_set"
  }
}

Input Schema

NameRequiredDescriptionDefault
notifyNo
dry_runNo
membersYes
report_idNo
datasource_idYes
expected_fingerprintYes

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.6.5

TDQS

A4.1/5.0
Behavior5/5

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

Beyond destructiveHint=true the description discloses a lot: it drives the Datasource's real Share dialog under a person's identity, notify triggers Google's invitation email, reCAPTCHA may reject long automated series with SHARING_REJECTED, and every change is journalled and read back. It also warns never to guess an address, which is exactly the failure mode for an invitation-granting tool.

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?

Dense but front-loaded: the core action comes first, then the member constraint, then behavioral caveats. The inline members shape duplicates schema structure somewhat and the line-wrapped formatting is awkward, but no sentence is filler.

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?

An output schema exists so return values need no prose, and the behavioral picture is unusually complete. However, for a destructive mutation requiring expected_fingerprint and defaulting to dry_run=true, omitting the meaning of those two parameters leaves a real gap an agent must close by guesswork.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across 6 parameters, yet the description only explains members (email plus viewer/editor role) and notify. The required expected_fingerprint is never explained, and dry_run — which defaults to true, meaning the call is a no-op unless explicitly flipped — and report_id go unmentioned, leaving the agent to infer the most consequential parameters.

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?

The description opens with a concrete verb plus resource ('Give people viewer or editor access to a reusable datasource') and immediately scopes it to new members only. An agent can tell this is the write counterpart to the sharing-read sibling without inspecting the schema.

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

Usage Guidelines4/5

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

Strong when-not guidance is present: it only adds people 'without access yet', and changing/removing an existing member is explicitly refused, with the Share dialog named as the human path for that. It does not name a sibling tool to use instead for reads or edits, so it stops short of full alternative routing.

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