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

No annotations exist, so the description must disclose behavior itself. It usefully states that only software is rolled back, never the database, and that the default target is the preceding live release. It does not mention potential disruption, irreversibility, or permissions, so it only partially carries the burden.

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 sentences front-load the core action and then add the database caveat. No filler or repetition of schema details. It is appropriately sized.

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 three-parameter tool with full schema coverage, the description gives enough to invoke rollback: target by default, explicit param `to`, and a clear scope boundary. It omits consequences like behavior when no prior release exists, but that is a minor gap. Overall complete enough for selection and basic invocation.

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 covers all three parameters fully, so the description is not required to re-document them. It does add a plain-language restatement of the default behavior for `to`, which aligns with the schema. This provides only marginal extra meaning over the already complete schema.

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 opening clause 'Put an earlier release back in service' names a specific operation and target (release), and the final clause 'never the database' narrows scope. It is distinct from siblings like deploy or restart, though it does not explicitly name them. Minor lack of explicit differentiation keeps it just below 5.

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?

Description states default behavior when `to` is omitted, which helps invocation, but gives no guidance on when to choose rollback over deploy/restart/releases. Usage is only implied by the verb and release context, with no explicit exclusions or alternatives. This is the minimum viable level.

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