purge_credential

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

Annotations already declare destructiveHint=true, so the destructive nature is known. The description adds two things annotations cannot convey: the operation is irreversible ('permanently destroy') and it 'always requires the user's approval' — a genuine workflow constraint. No return/error behavior is described, but the safety profile is well covered.

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 short sentences, zero waste, with the destructive consequence and approval requirement front-loaded. Every clause earns its place.

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 single-purpose destructive tool with no output schema, the description covers the essential consequence and approval gate, and annotations carry the safety flags. The gap is the undefined 'ref' argument, which is the only input and is left unexplained.

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 coverage is 0% and the single parameter 'ref' is documented nowhere. The description completely ignores it, leaving the agent to guess whether it is an ID, name, or path. With one undocumented parameter, the description must compensate and does not.

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 gives a specific verb (permanently destroy) and resource (a trashed credential), and the 'trashed' qualifier distinguishes it from delete_credential/restore_credential siblings, which operate differently. It stops short of explicitly naming those siblings as the routing alternatives.

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?

The precondition 'a trashed credential' implies this is only for items already in the trash, which is meaningful scoping. However, it never states the alternative (e.g., delete_credential to move to trash, restore_credential to recover), so the agent must infer the routing itself.

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