Skip to main content
Glama

Share a dashboard with a person

dashboard_share
DestructiveIdempotent

Share a dashboard you own, or one shared with you to edit, with ONE person, by email, as a viewer or an editor — the share dialog's "Can view" and "Can edit". role "view" (the default for someone new) lets them open it; "edit" also lets them change it, publish and roll back versions, rename it and manage who it is shared with — its queries still run as its owner, and an editor cannot pause, archive, delete or transfer it. Passing role for someone already on the list changes their role (to "view" takes edit away); leaving it out never changes an existing role. It is an invitation: an account holder is notified in OrionBI; someone without an account is emailed an invite and the share waits for their first sign-in. A private dashboard becomes visible to that person in the same call; one already shared keeps its audience and gains a person. People only — a group or a whole organization is policy rather than an invitation, and the owner sets it in OrionBI; there is no way to reach everyone on OrionBI or to mint a public link, by design. Your organization's sharing policy applies, as in OrionBI. Refused, with the reason, when the dashboard is archived or its sharing is paused.

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": {
      "dashboard": "<dashboard>",
      "to": "<to>"
    },
    "name": "dashboard_share"
  }
}

Input Schema

NameRequiredDescriptionDefault
toYesWho to share it with: one person, by email
roleNoWhat they may do: "view" (Can view) or "edit" (Can edit, and share). Omit to invite someone new as a viewer and leave an existing person's role as it is.
dashboardYesName of a dashboard you own or can edit, from dashboard_list, or its /d/owner/slug path

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Annotations declare destructiveHint=true and idempotentHint=true, and the description explains exactly what that means in practice: passing role "view" strips edit rights from an existing person, while omitting role never changes an existing role. It goes well beyond annotations by describing the invitation flow (in-app notification for account holders, email invite held until first sign-in), the visibility change on a private dashboard, and the refusal conditions.

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?

Core action and the one-person/by-email constraint are front-loaded, but the whole definition is a single long paragraph of em-dash-chained clauses, and the "view"/"edit" definitions restate what the role enum description already says. The editor-capability sentence is informative yet bulky for the selection decision it supports.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a three-parameter, nested-object, open-world invitation tool with no output schema, the description covers everything an agent needs: who can be shared with, what each role grants, how existing vs. new recipients behave, the notification/invite path, and the states in which the call is refused.

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 already 100%, so the baseline is 3, but the description adds real meaning: the default when role is omitted, the mutate-vs-noop distinction for existing people, and what editor rights entail (publish/rollback, rename, re-share) versus what they cannot do (pause, archive, delete, transfer). The `dashboard` parameter's name-or-/d/owner/slug acceptance is repeated from the schema rather than extended.

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?

Opens with a precise verb+resource+scope: share a dashboard you own or can edit with ONE person, by email, as viewer or editor. It is immediately distinguishable from dashboard_unshare, dashboard_share_list and dashboard_patch without opening any 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?

Gives clear context for use (invitation semantics, existing-person role change vs. new invite) and explicit exclusions — groups/organization-wide sharing is policy set in OrionBI, no public link exists, and calls are refused when the dashboard is archived or sharing is paused. It stops short of naming sibling tools such as dashboard_unshare or dashboard_share_list for the reverse/listing operations, so routing to alternatives is implied rather than stated.

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