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

The description goes well beyond the annotations. While annotations already declare destructiveHint=true and idempotentHint=true, the description adds critical behavioral context: the revocation is immediate ('stops authenticating immediately'), irreversible, cascades to leases and watchdogs, and has specific data-access consequences (private journal access lost, public receipts remain). It also clarifies a non-effect (does not cancel Stripe subscription). This is exemplary disclosure for a destructive operation.

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 description is compact and front-loaded. The first sentence states the core action. The second sentence delivers the most critical warning (immediate, irreversible). The remaining sentences efficiently enumerate consequences and exclusions. Every sentence earns its place; there is no redundancy except the intentional repetition of 'Irreversible' for emphasis, which is acceptable given the stakes.

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, irreversible tool with no output schema, the description is remarkably complete. It tells the agent what happens immediately, what is permanently lost, what remains, and what is not affected. The only minor gap is the lack of an explicit statement about the return value, but for a void-like destructive action this is not critical. The annotations (destructiveHint, idempotentHint) plus the description cover all decision-relevant context.

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 100%, so the schema already documents the single optional vigil_key parameter thoroughly, including its deprecation and the preferred Bearer header alternative. The description adds value by clarifying the scope ('your own key') and the irreversible consequences, which helps an agent understand what the parameter-less call actually does. However, the description doesn't explicitly map the parameter to the behavior, so it doesn't quite earn a 5.

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 opens with a specific verb and resource: 'Revoke your own key.' It immediately distinguishes this from sibling tools like vigil_revoke_lease and vigil_delete_watchdog by naming the exact object being revoked (the key) and the scope ('your own'). The subsequent consequences (stopping authentication, revoking leases, deleting watchdogs) further disambiguate it from related revocation tools.

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 description clearly states when to use this tool: when you want to revoke your own key. It also provides an explicit exclusion: 'It does not cancel a Stripe subscription,' which helps an agent avoid a common confusion. However, it doesn't explicitly name alternative tools for related operations (e.g., vigil_revoke_lease for revoking a lease without deleting the key), so it falls just short of a 5.

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