Roll back to the previous release (SSH)

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

Annotations already declare destructiveHint=true, idempotentHint=false, and openWorldHint=true, and the description adds substantial context beyond them: migrations are NOT undone, the release manager swaps `current`, reloads processes and checks health, and a rollback exceeding timeout_seconds keeps running server-side rather than being interrupted. It also discloses the SSH host-alias allowlist constraint and includes a prompt-injection warning about server/file text.

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?

Front-loads the DESTRUCTIVE marker and the mechanism before the guardrails, and each sentence carries operational information. It is dense and somewhat long, but nothing is clearly redundant for a destructive remote operation.

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, open-world mutation with an output schema present, the definition covers mechanism, confirmation gate, non-reversible side effects (migrations), and post-timeout recovery path via deploy_status. Nothing an agent needs in order 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?

Schema coverage is 75%, so most parameters are documented structurally; the description still adds value by spelling out the exact confirm token format and the semantics of timeout_seconds (the process outlives the timeout instead of aborting). The host_alias allowlist and app naming convention are largely mirrored from the schema descriptions rather than extended.

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 specific verb and resource ('makes the previous good release live again on the server') and names the exact mechanism (`sudo -n <app>-deploy --rollback` over SSH). It is clearly distinguishable from siblings like deploy_status and deploy_logs, which the description references by name.

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?

Gives explicit preconditions ('Call it only after the user explicitly confirms') and an ordering instruction ('Show them deploy_status first, so they know which release becomes live'). It also states the hard gate: 'confirm must be exactly "<app>@<host_alias>", or nothing runs.'

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