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

Annotations already declare non-destructive, idempotent mutation, but the description adds genuinely useful context beyond them: nothing is deleted by a rollback and the change can be reversed by rolling forward again. That reversibility framing is not derivable from destructiveHint=false alone and materially reduces hesitation about calling a write tool.

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 with the action front-loaded and the risk-reassurance second. No filler, no restatement of the title.

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 two-parameter, fully documented, richly annotated mutation with no output schema, the definition covers what an agent needs to act safely. The only gap is failing to point at list_versions as the way to discover valid version numbers.

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 both parameters are documented inline, including that 'app' accepts a slug or id and that 'version' is the version to serve. The description adds no further parameter meaning, which is the correct baseline when the schema carries the load.

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 (serve an earlier version) and resource (app), and the phrase 'again' makes clear it is a revert operation, distinguishing it from publish_app and update_app. It stops short of naming the siblings it is not, so it is clear but not fully differentiated.

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 only implied: the agent must infer it needs an existing version, and list_versions or publish_app are never referenced as the prerequisite or alternative path. There are no explicit when/when-not conditions, but the operation is conventional enough that inference is low-risk.

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