Submit structured feedback to request modifications on an asset awaiting approval. Specify required changes by category, severity, and reason to guide revisions.
Request changes on a candidate asset.
| Name | Required | Description | Default |
|---|---|---|---|
| actor | Yes | Requesting actor | |
| reason | No | Summary reason | |
| feedback | Yes | Required changes | |
| approval_id | Yes | Approval record ID |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. 'Request changes' implies a write/mutation action, but the description doesn't state whether the change-request is persisted, whether it blocks or cancels the approval, notification behavior, or reversibility. For a mutation tool with zero annotation coverage this is a significant gap.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single concise sentence that states the action clearly. It's front-loaded and every word earns its place. No fluff or redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a mutation tool with no annotations distilled from the description, this is too thin. An agent needs to know what 'request changes' does to the asset lifecycle, whether it persists, whether it feeds into an approval flow, and what the response looks like (no output schema). Four parameters including nested objects, no annotations, and no output schema – this description doesn't carry its weight.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the baseline is 3. The description adds no additional meaning beyond what the schema already provides. The nested feedback array is complex but the schema documents each sub-field (category, severity, etc.). The description doesn't clarify the relationship between reason and feedback, or how they interact. -1 for no added value over the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific verb ('Request changes') and a resource ('candidate asset'), which clearly identifies the tool's purpose. It's distinguishable from siblings like art.asset.archive_version or art.asset.update by its focus on the approval/review workflow, though it doesn't explicitly name alternatives.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus the many sibling tools (e.g., art.qa.asset for quality checks, art.production.approve for approval). It doesn't state prerequisites (e.g., that an approval record must exist), nor when NOT to use it. The toolname and description imply an approval context, but no explicit routing or exclusion of alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.