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

Annotations already flag destructiveHint=true, but the description adds value beyond them: the deletion is permanent, it requires the keys:write account scope, that scope is off by default, and only the account owner can grant it in the console. These are exactly the operational facts an agent needs before attempting a destructive call, and nothing contradicts the 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 sentences, no filler, front-loaded with the destructive action and target before moving to exclusions and the permission prerequisite. Every sentence contributes a distinct fact.

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 two-parameter destructive tool with no output schema, the description covers permanence, exclusions, the confirm gate, and the auth requirement. It stops short of stating success/failure behavior or how to source a valid key_id.

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 0%, so the description must carry the meaning. It does explain the confirm flag ('Pass confirm: true') and scopes what key_id may reference (an API-created key or the calling key), but it never states the key_id format or where to obtain it, leaving half the parameter semantics implicit.

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 the exact verb and resource ('Permanently delete a key') plus the accepted targets ('created through an API key, or the calling key itself') and the excluded class ('Keys created in the console cannot be deleted this way'). This clearly separates it from sibling key_disable / key_update without requiring schema inspection.

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 a real precondition (pass confirm: true) and an explicit when-not case (console-created keys). It does not, however, route the agent to an alternative such as everyinfra_key_disable for reversible revocation, so the alternative-selection half of the guidance is left to inference.

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