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

Annotations already declare readOnlyHint=false and destructiveHint=true, and the description adds the concrete consequence the hint cannot convey: existing ciphertexts become permanently unreadable. It also discloses the access prerequisite (Proof account, client authentication, and that start_login does not grant access), which is exactly the kind of behavioral context annotations cannot supply.

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 blocks: the destructive warning leads, and the prerequisite follows. No filler, and the irreversibility statement is front-loaded where an agent will read it before deciding to call.

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-parameter destructive tool with an output schema and both destructive/read-only annotations present, the description covers what remains: the blast radius of the deletion and the authentication gate. Nothing an agent needs to call it safely 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?

Only one parameter, hitl_id, and the schema documents it at 100% coverage. The description adds no format, sourcing, or validation detail beyond identifying it as a HITL config, so the schema carries the load — the 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?

States a precise verb and resource: 'Delete the encryption keypair from a HITL config.' The sub-resource (keypair, not the config itself) distinguishes it cleanly from delete_hitl and from the read-only get_hitl_keys, which appear in the sibling list.

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?

Usage is implied by the resource name, and the ACCESS paragraph usefully rules out start_login as a way to gain access to this tool. However, it never says when to delete a keypair versus when to delete the whole HITL config or rotate/upload keys instead, so routing between the key-lifecycle siblings 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.