aidelly_delete_draftDelete a draft by id. Drafts are work-in-progress content that never publishes.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | ||
| query | No | Optional query overrides for endpoints with sparse parameter schemas. | |
| brand_id | No | ||
| workspace_id | No | Workspace to operate in: the `id` of a workspace returned by aidelly_list_workspaces. Optional for read operations; required when creating content. | |
| idempotency_key | Yes |
Changes observed during successful MCP inspections.
Input schema / properties / idempotency_key / exampleAdded value: +"order-123:create-post:v1"Input schema / properties / idempotency_key / maxLengthAdded value: +255Input schema / properties / idempotency_key / minLengthAdded value: +1Input schema / properties / idempotency_key / patternAdded value: +"^[\\x21-\\x7E]{1,255}$"Input schema / properties / workspace_id / descriptionPrevious value: -"Workspace to operate in. Do not ask the user for this UUID — call aidelly_list_workspaces and use the `id` of the matching workspace. Optional for read operations; required when creating content."New value: +"Workspace to operate in: the `id` of a workspace returned by aidelly_list_workspaces. Optional for read operations; required when creating content."Input schema / properties / id / descriptionRemoved value: -"Draft ID."Input schema / requiredPrevious value: -[
- "id",
- "idempotency_key"
-]New value: +[
+ "idempotency_key",
+ "id"
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare destructiveHint=true, idempotentHint=true and openWorldHint=true, so the safety profile is covered. The description adds only the fact that drafts are unpublished; it says nothing about permanence, recoverability, or what happens when the id doesn't exist, which is the kind of context that would earn credit above the annotation baseline.
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?
Two short sentences, the action front-loaded before the domain gloss. Nothing is padded, though the second sentence's payoff for an agent selecting a tool is modest.
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?
No output schema exists, so the description carries the full burden for a destructive, 5-parameter tool. It leaves the required idempotency key, workspace scoping, and failure/recovery behavior undocumented, which is not sufficient for correct invocation.
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 coverage is 40%, so the description must compensate, and it only accounts for the 'id' parameter ('by id'). The required 'idempotency_key' is completely unexplained in both the schema and the description — a significant gap for a destructive operation.
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?
Specific verb+resource ('Delete a draft by id') with a clarifying gloss that the target is unpublished work-in-progress content. It doesn't explicitly distinguish itself from sibling tools like aidelly_delete_post_comment or aidelly_update_draft, but the resource is unambiguous.
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 when-to-use guidance, no prerequisites, no exclusions. The clause 'work-in-progress content that never publishes' hints that this is destructive but low-exposure, yet it never says when a caller should delete a draft versus update it or leave it in the list.
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.