delete_agent| Name | Required | Description | Default |
|---|---|---|---|
| agent_id | Yes | ID of the agent to delete | |
| on_behalf_of | No | An agency client's email, from list_agency_clients, to run this call in that client's account: their agents, settings, connected accounts, and credits. Omit it to act on your own account. |
Changes observed during successful MCP inspections.
Input schema / properties / on_behalf_ofAdded value: +{
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "description": "An agency client's email, from list_agency_clients, to run this call in that client's account: their agents, settings, connected accounts, and credits. Omit it to act on your own account."
+}Input schema / properties / agent_idAdded value: +{
+ "description": "ID of the agent to delete",
+ "type": "integer"
+}Input schema / properties / task_idRemoved value: -{
- "description": "ID of the task to delete",
- "type": "integer"
-}Input schema / requiredPrevious value: -[
- "task_id"
-]New value: +[
+ "agent_id"
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations declare destructiveHint=true, but the description goes beyond them by disclosing soft-delete semantics: the user stops seeing it, it stops running, and the record is retained internally for a short window. This is exactly the kind of consequence detail annotations cannot carry.
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?
Front-loads the action and consequence, then the confirmation requirement, then the return shape. The XML-tag scaffolding is slightly verbose but each section carries useful content.
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 destructive, no-output-schema tool, the description covers effect, data retention, required user confirmation, and the return shape ('Dict with success status'). Nothing an agent needs to call it safely is missing.
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 both agent_id and on_behalf_of are already fully documented, including the agency-client semantics of on_behalf_of. The description adds nothing beyond the schema, so the baseline 3 applies.
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?
States a specific verb and resource ('Delete an agent') and is clearly distinguishable from siblings like update_agent, create_agent, and get_agent_details. An agent can identify the operation without opening the schema.
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?
Gives an explicit precondition ('ALWAYS confirm with the user before calling this'), which is meaningful for a destructive tool. It does not, however, name when to delete vs. alternatives such as deactivating, so it falls short of full when/when-not guidance.
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.