replica_restart

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

With no annotations, the description carries the full burden of behavioral disclosure. It clearly marks the tool as '[WRITE][risk=high]' and states that it 'Drops the replica's in-flight requests', which is critical behavioral information. It also explains the dry_run parameter for previewing without side effects.

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?

The description is very concise: a one-line summary with a risk tag, followed by a list of parameters in a clean 'Args:' format. Every sentence provides necessary information without verbosity.

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?

Given the complexity (5 parameters, no output schema, no annotations), the description covers the purpose, all parameters, the behavioral impact (dropping requests), and safe usage via dry_run. There are no evident gaps.

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?

Although the schema has 0% description coverage, the description provides meaningful context for each parameter: it explains dry_run as a preview toggle, replica_id as coming from replica_list, and target as an optional inference target from config. This adds value beyond the schema's type definitions.

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 description starts with a clear verb phrase 'Restart one wedged Serve replica (kills + respawns the actor).' This specifies the action on a specific resource, and the sibling tools include related replica management tools (e.g., replica_list, drain_replica), making the tool's purpose distinct.

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?

The description explicitly states the use case: restarting a wedged replica. It also mentions using dry_run=True to preview, which guides safe usage. However, it does not explicitly contrast with sibling tools like drain_replica or scale_replicas_up.

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