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

Annotations only declare readOnlyHint=false, openWorldHint=false, destructiveHint=false — the description goes far beyond by disclosing the ~15s propagation delay, the free-site two-phase scanning flow with idempotency_key resumption, the no_previous_deploy failure mode, and the 409 live_changed concurrency guard. These are exactly the traits an agent cannot infer from structured fields.

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-loaded with the core action and default, then layered with the exception paths, and it ends with a clearly bracketed usage section. It is dense and long, and a few clauses restate schema descriptions, but no sentence is filler.

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?

There is no output schema, so the description must explain return states — and it does, covering status 'scanning', no_previous_deploy, and 409 live_changed along with what to do next in each case. Nothing an agent needs to invoke this correctly or interpret a non-success response 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 100% and already documents each parameter, so the schema carries the baseline. The description still adds operational meaning the schema does not: that a new idempotency_key starts a new rollback rather than resuming, and why expected_live_deploy should carry the live_deploy_id the person actually saw. Slight redundancy with the schema's own 409 wording keeps it at 4.

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 ('Roll the live version back to an earlier retained version') and immediately clarifies the default scope when deploy_id is omitted. An agent can distinguish this from publish_draft, restore_draft, or deploy_cancel without opening any schema.

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 prerequisites (show diff_versions and preview_version for the target and get a yes), names the upstream tools whose outputs feed parameters (list_versions' live_deploy_id), and includes a clear when-to-use/what-not-to-do section with a prompt-injection guardrail. The resumption workflow for a 'scanning' answer is spelled out step by step.

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