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

Annotations already declare destructive=true and idempotent=true, but the description adds the concrete effect ('permanently removes the stored secret') and an operational warning to preserve recovery codes. It does not describe auth requirements or downstream effects, but it adds useful behavior beyond annotations.

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?

Three short sentences, front-loaded with the action and immediately followed by permanence and recovery-code warning. No filler or repetition.

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 one-parameter delete operation with rich annotations and no output schema, the description covers permanence and a critical recovery-code precaution. It could be more complete by pointing to list_authenticators for identifying the target, but nothing critical 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?

The sole parameter id has 100% schema description coverage ('Resource UUID.'), so the schema already carries parameter meaning. The description does not add syntax or identification guidance for id; 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?

The description states a specific verb and resource ('Delete an authenticator') and scopes it to accounts the human asked the agent to create or operate. It clearly distinguishes the delete action from sibling tools such as add_authenticator and list_authenticators.

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?

It gives clear usage context (accounts the human asked the agent to create or operate) and a pre-deletion instruction to keep recovery codes. It does not explicitly route to list_authenticators for finding the id or state when deletion should not be used.

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