Set human approval mode for live writes to 'required' (recommended) so agents cannot disable safeguards; 'off' is rejected here and only a human can change it.
Set human approvals for live writes: 'required' (recommended). 'off' is refused here; only the human can switch it off, on the setup_credentials page.
| Name | Required | Description | Default |
|---|---|---|---|
| mode | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections.
v0.1.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the burden, and it does disclose a real behavioral constraint: 'off' cannot be set here because switching it off requires a human on a separate page. That is meaningful beyond a simple setter description, though it does not describe permissions, persistence, or what the tool returns.
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 tight sentences, front-loaded with the purpose and the recommended value, then the restriction. No filler and no repetition of the tool name.
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?
With an output schema present, the description need not explain return values, and it covers the key behavioral constraint. The remaining hole is the incomplete enumeration of valid 'mode' values, which an agent needs in order to call the tool correctly.
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?
One parameter ('mode') at 0% schema coverage, so the description must compensate. It surfaces two accepted values ('required', 'off') and flags the recommended one, but never states that these are the only valid values, nor whether the 'off' value is rejected with an error here – leaving genuine ambiguity about the accepted input space.
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+resource: configuring human approval mode for live writes. It is not easily confused with setup_status or setup_credentials since it names the exact setting and its recommended value. However it does not name a sibling tool as the alternative, only the sibling page (setup_credentials).
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 clear context ('required' is recommended) and an explicit restriction ('off' is refused here), pointing to where the alternative action lives (setup_credentials page). What remains implicit is when in the onboarding flow an agent should call this versus setup_set/setup_services.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.