Skip to main content
Glama

Rightshold

by com.rightshold
OverviewDiscussionsAdmin

Issue a rights manifest for a deliverable

issue_rights_manifest

Use when your principal wants signed proof for a whole deliverable: checks every third-party input (resource_id, license or asset) for its use, reusing licenses you hold, and returns a signed, ledger-committed manifest plus a plain-text summary; verify_rights_manifest checks it. Call with {"title": "Spring campaign", "intended_use": {"commercial_use": true}, "items": [{"ref": "font", "license": "OFL-1.1"}]}.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
itemsYes
titleYes
clientNo
api_keyNoDeprecated: use Authorization: Bearer <key> (arguments can reach transcripts).
deliverableNo
intended_useNoUses to check: each true flag must be documented; omitted = false; unknown fields refused. For instance {"commercial_use":true}
idempotency_keyNoOptional: a retry with the same key returns the first proof.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • changedInput schema / properties / intended_use / description
      Previous value: -"Intended use: every true flag is a right the check must find documented; omitted flags are false; unknown fields are refused. For instance {\"commercial_use\":true,\"deployment\":true,\"attribution_planned\":true,\"duration_days\":365}"New value: +"Uses to check: each true flag must be documented; omitted = false; unknown fields refused. For instance {\"commercial_use\":true}"
    • addedInput schema / properties / items / items / properties / asset / description
      Added value: +"URL or name"
    • addedInput schema / properties / items / items / properties / license / description
      Added value: +"SPDX id"
    • addedInput schema / properties / items / items / properties / ref / description
      Added value: +"Your label"
  2. Changed3 schema fields changed
    • addedInput schema / properties / api_key / deprecated
      Added value: +true
    • changedInput schema / properties / api_key / description
      Previous value: -"Your Rightshold API key (rs_...). Only needed if your MCP client cannot send Authorization: Bearer <key>."New value: +"Deprecated: use Authorization: Bearer <key> (arguments can reach transcripts)."
    • changedInput schema / properties / intended_use / description
      Previous value: -"Intended use. Every true flag is a right the assessment must find documented; omitted flags are false. Unknown fields are refused (invalid_intended_use). For instance {\"commercial_use\":true,\"deployment\":true,\"attribution_planned\":true,\"duration_days\":365}"New value: +"Intended use: every true flag is a right the check must find documented; omitted flags are false; unknown fields are refused. For instance {\"commercial_use\":true,\"deployment\":true,\"attribution_planned\":true,\"duration_days\":365}"
  3. Changed4 schema fields changed
    • changedInput schema / properties / idempotency_key / description
      Previous value: -"Optional: a retry with the same key returns the proof already issued instead of a second one."New value: +"Optional: a retry with the same key returns the first proof."
    • removedInput schema / properties / items / items / properties / intended_use / additionalProperties
      Removed value: -false
    • changedInput schema / properties / items / items / properties / intended_use / description
      Previous value: -"Intended use. Every true flag is a right the assessment must find documented; omitted flags are false. Unknown fields are refused (invalid_intended_use). For instance {\"commercial_use\":true,\"deployment\":true,\"attribution_planned\":true,\"duration_days\":365}"New value: +"Optional per-item override, same shape as intended_use"
    • removedInput schema / properties / items / items / properties / intended_use / properties
      Removed value: -{
-  "attribution_planned": {
-    "type": "boolean"
-  },
-  "commercial_use": {
-    "type": "boolean"
-  },
-  "deployment": {
-    "type": "boolean"
-  },
-  "duration_days": {
-    "description": "Whole days of use (1 to 36500), or null for no fixed term",
-    "maximum": 36500,
-    "minimum": 1,
-    "type": [
-      "integer",
-      "null"
-    ]
-  },
-  "geography": {
-    "description": "worldwide (default) or a region code such as US, EU, UK",
-    "maxLength": 32,
-    "minLength": 1,
-    "type": "string"
-  },
-  "model_inference": {
-    "type": "boolean"
-  },
-  "model_training": {
-    "type": "boolean"
-  },
-  "modification": {
-    "type": "boolean"
-  },
-  "redistribution": {
-    "type": "boolean"
-  },
-  "sublicensing": {
-    "type": "boolean"
-  }
-}
  4. Changed1 schema field changed
    • addedInput schema / properties / idempotency_key
      Added value: +{
+  "description": "Optional: a retry with the same key returns the proof already issued instead of a second one.",
+  "maxLength": 255,
+  "type": "string"
+}
  5. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "type": "object"
+}
  6. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Annotations declare readOnlyHint=false and destructiveHint=false, but the description adds meaningful behavior: licenses are reused when held, the manifest is signed and committed to a ledger, and a plain-text summary is also returned. It does not state auth requirements, rate limits, or what happens on failure (the schema's api_key deprecation note carries the auth hint instead).

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?

Front-loaded with the usage trigger and leading with the deliverable-level scope, then the mechanics, then the rival tool, then a concrete example. The middle sentence is dense and run-on, but every clause (reuse of held licenses, ledger commitment, summary return) earns its place.

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 7-parameter nested-object tool with a 43%-covered schema, the description supplies the missing shape through the example and names what comes back (signed manifest plus summary). With an output schema present, return detail is not required; the remaining gap is per-parameter guidance for client/deliverable.

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 description coverage is only 43%, so the description must compensate — and it does, via a full example call showing title, intended_use, and an items entry with ref and license, plus the note that items accept resource_id, license, or asset. Client, deliverable, and idempotency_key are not elaborated in the description, so compensation is good but not complete.

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 action (issue a signed rights manifest), the exact artifact produced (ledger-committed manifest plus plain-text summary), and the scope ('a whole deliverable' versus single inputs). It distinguishes itself from the sibling verify_rights_manifest, which it explicitly names as the checker, and from per-resource tools by saying it 'checks every third-party input'.

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?

'Use when your principal wants signed proof for a whole deliverable' is an explicit triggering condition, and it routes the agent to verify_rights_manifest for verification. It doesn't explicitly contrast with issue_rights_receipt or the single-item assess_resource_for_use, so the boundary between whole-deliverable and single-resource issuance is left partly to inference.

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

All Rightshold toolsInspect
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