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

Annotations only declare the generic safety profile (not read-only, idempotent, non-destructive). The description goes further by disclosing the zero-downtime rolling behavior, that the running version is reused rather than rebuilt, and the important conditional exception that storage-backed apps are stopped and started, making them unreachable for a few seconds.

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 action and mechanism, then layers usage triggers, the sibling boundary, and the storage caveat in short, waste-free sentences. No sentence is redundant.

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?

With one fully documented parameter, no output schema, and annotations covering safety, everything an agent needs to select and invoke this tool correctly is present, including the non-obvious storage-app downtime behavior.

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 the single app_id parameter is already documented in the schema as 'The app id returned by list_apps'. The description adds no syntax, format, or sourcing detail beyond that, so the baseline of 3 applies.

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 ('Restart an existing app') and immediately qualifies the mechanism ('rolling restart with zero downtime'). It also distinguishes itself from the sibling rebuild_app by stating what it does not do.

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 trigger conditions ('after changing configuration, or to recover an app that is stuck or misbehaving') and names the alternative for the contrasting case ('call rebuild_app for that'). Both when-to-use and when-not-to-use are covered.

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