Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations declare destructive/openWorld but the description supplies the operational detail they can't: the confirmed=true gate for delete-only providers, the irreversibility warning, the 'waiting' outcome under two-person shut-off, and the required reviewer roles. This is exactly the extra context an agent needs before a destructive call.

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?

Each sentence carries distinct information (access, delete-only confirmation, two-person flow), front-loaded on what the tool does. The trailing 'Confirm with the user first' is a global instruction placed after a case-specific one, a minor ordering weakness in an otherwise dense, waste-free description.

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, open-world mutation with an output schema, the description covers permissions, irreversibility, the confirmation gate, and the human-approval workflow. Nothing an agent needs to call it safely is missing, and return values are correctly left to the output schema.

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?

With 0% schema description coverage the description must carry the parameters, and it does: key_id is sourced from list_provider_keys, action is explained via 'restore', and confirmed's gating semantics are spelled out. The default (disable) is only implied rather than stated, keeping it just below a 5.

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 ('Turns a provider key ... off at its provider') and covers the inverse operation ('or back on (action restore)'). It also names the sibling that supplies the id (list_provider_keys), so the agent can distinguish it from delete/disconnect-style siblings without opening schemas.

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 prerequisites (shut-off access per provider), a routing instruction for the two-person case (confirm_shut_off), and an explicit 'Confirm with the user first' rule. It falls short of a full 5 because it never states when not to use this tool (e.g., vs. deletion or waiting_shut_offs) beyond the implicit failure path.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.