redis_kill_client

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

Annotations only carry the generic safety profile (destructive, non-idempotent); the description goes well beyond by declaring irreversibility, that no undo entry is recorded, that priorState is captured from CLIENT LIST, and that most clients reconnect. The self-connection refusal rule, including its behavior under dry_run, is exactly the kind of edge case annotations cannot express.

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 leading [WRITE][risk=medium] tag and the IRREVERSIBLE warning are front-loaded, and the body is dense with decision-relevant facts rather than filler. The Args block partially restates the schema, but with 0% schema coverage that repetition is earned.

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 destructive tool with no output schema and no annotation detail, the description covers irreversibility, prior-state capture, preview mode, and refusal semantics. It stops short of describing the shape of a successful response, but priorState is at least characterized.

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 description coverage is 0%, so the description must carry all parameter meaning and it does: it defines client_id (preferred, sourced from redis_clients), addr as 'ip:port', dry_run, and target as a config name defaulting to the default target. It does not state that at least one of client_id/addr must be supplied, a minor gap given all four params are optional with defaults.

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+resource (disconnect one redis client) and the two accepted identifiers (id or addr). It is clearly distinguishable from the read-only sibling redis_clients and from unrelated queue/policy tools.

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?

Tells the agent how to preview (dry_run=True), points to redis_clients as the source of client_id, and documents the refusal case including under dry_run. It lacks explicit when-not-to-use guidance relative to siblings such as undo_apply or connection_churn_analysis, but the operating context is clear.

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