delete_approval_channel_keys

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

The annotation destructiveHint=true only flags that something is destroyed. The description states exactly what is destroyed: 'Existing ciphertexts will become permanently unreadable.' It also describes the auth requirement, including the trap that start_login will not unlock this tool. That is materially more context than the annotation provides.

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?

The purpose and the destructive warning come first, and the access note is set off in its own block. Every sentence carries operational value. The only minor inefficiency is that the ACCESS paragraph repeats restart/re-call instructions at moderate length.

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 one-parameter tool with an output schema, the description carries the essential burden: irreversibility and the auth prerequisite. Return values need not be explained. It stops short of five because it does not mention whether deletion can be undone, by re-uploading keys for example, or what the output reports.

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?

There is only one parameter, hitl_id, and its schema description coverage is 100% ('Approval channel ID'), so the schema already covers its meaning. The description adds little: the phrase 'from an approval channel' is only consistent with the schema rather than extending it. 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 first sentence gives a specific verb and resource: 'Delete the encryption keypair from an approval channel.' Naming 'approval channel' distinguishes it from the sibling delete_hitl_keys without naming that sibling, but the description does not explicitly contrast the two key-deletion tools, so an agent must infer which resource scope applies.

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 ACCESS note gives a concrete prerequisite, a PROOF account with PROOF_API_KEY set and a server restart, and explicitly rules out a path: 'start_login does NOT open this tool.' That is a useful when-not signal, although no guidance is given on when to delete keys instead of archiving the channel or rotating keys via upload_approval_channel_keys.

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