ScoreStarling

Manage score access

manage_score_access

Idempotent

Set link and individual access to an owned score when asked. Copies are separate; no email is sent.

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": {
      "score_id": "<score_id>",
      "action": "<action>",
      "request_id": "<request_id>"
    },
    "name": "manage_score_access"
  }
}

Input Schema

Name	Required	Description	Default
`role`	No	viewer, commenter or editor. Never grants ownership, access management or spending.	viewer
`email`	No	The exact email the owner asks to invite or remove.
`action`	Yes	list, configure link access, add/update one email, or remove it.
`offset`	No	Member list offset, 20 records per page.
`revision`	No	The current saved revision, from the latest read or edit.
`score_id`	Yes	The score, from a result or the score list.
`link_role`	No	Link role; writes need sign-in. Effective access is the higher of link and individual roles.	viewer
`allow_copy`	No	Allow independent copies.
`request_id`	Yes	Stable request UUID.
`access_kind`	No	invited admits named accounts; link admits anyone. Saved changes sync.	invited
`include_media`	No	Include the original audio/video only when requested.
`expected_access`	No	Current access_version from sharing settings; stale changes are refused.
`include_history`	No	Include versions saved before collaboration started only when requested.

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedNov 6, 2026

changedInput schema / properties / access_kind / description

Previous value: -"invited requires sign-in and a matching account; link publishes a fixed read-only edition."New value: +"invited admits named accounts; link admits anyone. Saved changes sync."

addedInput schema / properties / link_role

Added value: +{
+  "default": "viewer",
+  "description": "Link role; writes need sign-in. Effective access is the higher of link and individual roles.",
+  "enum": [
+    "viewer",
+    "commenter",
+    "editor"
+  ],
+  "type": "string"
+}

changedInput schema / properties / request_id / description

Previous value: -"Stable UUID for this request."New value: +"Stable request UUID."

AddedNov 3, 2026

TDQS

A3.5/5.0

Behavior3/5

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

Beyond the annotations, the description usefully states that copies are separate and no email is sent. However, for a mutation tool it omits important behavior such as sign-in requirements for link writes, stale revision refusal, effective access resolution, and what list returns; annotations already cover idempotency, mutability, and open-world behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two short sentences, front-loads the purpose, and wastes no words. The second sentence adds two relevant facts without repeating the schema or annotations.

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?

For a 13-parameter access-management tool with no output schema, the description is thin. The schema and annotations carry much of the burden, but the description does not explain list/configure/add/remove outcomes, member-list pagination, revision conflicts, or return behavior.

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?

Schema description coverage is 100%, so the schema already documents all 13 parameters, enums, defaults, and important constraints like stale expected_access refusal. The description alludes to link and individual access plus copy separation, but adds no specific meaning beyond the schema.

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 and resource: 'Set link and individual access to an owned score.' It also distinguishes copying behavior with 'Copies are separate,' but it does not name sibling share tools such as get_score_share or publish_score_share, and 'Set' does not clearly cover the schema's 'list' action.

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?

The phrase 'when asked' implies use only on an explicit owner request, which is useful but minimal. It does not explain when to use this instead of sharing siblings like get_score_share, publish_score_share, or collaborate_score, nor how the list/configure/add/remove actions should be selected.

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

All ScoreStarling tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?