Refine an existing artifact draft while preserving tenant boundary, provenance, MASK status, and approval posture.
| Name | Required | Description | Default |
|---|---|---|---|
| lane | No | ||
| format | No | ||
| audience | No | ||
| draft_id | No | ||
| tenant_id | Yes | ||
| artifact_type | No | ||
| source_content | No | ||
| source_context | No | ||
| idempotency_key | No | ||
| new_source_context | No | ||
| refinement_instruction | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections.
Input schema / properties / artifact_typeAdded value: +{
+ "enum": [
+ "blog",
+ "linkedin_post",
+ "proposal",
+ "upwork_answer",
+ "email",
+ "bio",
+ "cover_letter",
+ "case_study",
+ "comment",
+ "newsletter",
+ "landing_page_copy",
+ "form_answer",
+ "strategy_note",
+ "operating_doctrine",
+ "decision_log",
+ "research_synthesis",
+ "outreach",
+ "follow_up",
+ "objection_response",
+ "correspondence_response",
+ "one_pager",
+ "work_sample",
+ "portfolio_summary",
+ "founder_pov",
+ "framework_essay",
+ "cfo_memo",
+ "board_finance_brief",
+ "qew_report",
+ "scenario_analysis",
+ "capital_allocation_brief",
+ "kpi_narrative",
+ "market_commentary",
+ "custom"
+ ],
+ "type": "string"
+}Input schema / properties / audienceAdded value: +{
+ "type": "string"
+}Input schema / properties / formatAdded value: +{
+ "enum": [
+ "short",
+ "long",
+ "bullets",
+ "paste_safe",
+ "markdown",
+ "html",
+ "email_safe",
+ "json"
+ ],
+ "type": "string"
+}Input schema / properties / laneAdded value: +{
+ "enum": [
+ "external",
+ "internal",
+ "sales",
+ "authority",
+ "application",
+ "regulated_financial"
+ ],
+ "type": "string"
+}Input schema / properties / source_contentAdded value: +{
+ "type": "string"
+}Input schema / properties / source_contextAdded value: +{
+ "type": [
+ "object",
+ "string"
+ ]
+}Input schema / requiredPrevious value: -[
- "tenant_id",
- "draft_id",
- "refinement_instruction"
-]New value: +[
+ "tenant_id",
+ "refinement_instruction"
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The readOnlyHint annotation already indicates the tool does not mutate state. The description goes beyond this by specifying the invariants it preserves: tenant boundary, provenance, MASK status, and approval posture. This is useful behavioral context about what will and won't change, though it does not cover errors, outputs, or side effects beyond that.
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?
The description is a single, front-loaded sentence. It leads with the core action, 'Refine an existing artifact draft,' and each remaining clause adds meaningful constraints. There is no wasted text.
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 an 11-parameter tool with zero schema description coverage and no parameter explanations, this short description is insufficient. It gives a high-level purpose but leaves the agent guessing about how lane, format, audience, source_context, new_source_context, and idempotency_key should be used. The output schema helps with return shape, but not with call construction.
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 0%, and the description does not explain any of the 11 parameters. The agent is left to infer meaning from parameter names alone. Even key parameters like refinement_instruction, draft_id, idempotency_key, and new_source_context are not described or connected to the tool's behavior.
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 and resource: 'Refine an existing artifact draft.' It also names the key behavioral constraints (preserving tenant boundary, provenance, MASK status, approval posture), which distinguishes it from sibling tools like artifact_generate (creating new drafts) and artifact_save (persisting drafts). An agent can tell what this tool does at a glance.
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?
The phrase 'existing artifact draft' implies this tool is for revising drafts that already exist, as opposed to generating new ones. However, the description gives no explicit when-to-use/when-not-to-use guidance and does not name alternatives such as artifact_generate or artifact_save.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.