container_kill

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

The description goes well beyond the annotations (readOnlyHint=false, destructiveHint=true) by explaining the destructive nature: 'default SIGKILL — immediate, no graceful shutdown', and documenting edge-case behaviors like failing with a conflict error and refusing to signal its own container in containerized servers. This gives the agent a rich behavioral model without needing to infer from annotations alone.

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 well-structured: it leads with the core action, then moves to usage guidance, then lists args and returns. Every sentence earns its place—no fluff, no repetition. The args block is formatted cleanly and is immediately scannable.

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?

The tool has moderate complexity (signals, error cases, containerized caveat) and no output schema, yet the description covers all critical aspects: purpose, default behavior, usage alternatives, error conditions, return value, and parameter semantics. There is no gap that would leave an agent uncertain.

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?

Even though schema coverage is 0%, the description fully documents both parameters. It defines id_or_name as 'The container id or name' and signal with examples ('SIGHUP', '9') and its default (SIGKILL). This adds crucial semantic detail that the bare schema (signal: string, default null) does not convey.

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 opens with a specific verb and resource: 'Send a signal to a running container', and immediately clarifies the default behavior (SIGKILL, no graceful shutdown). It actively differentiates from sibling tools like container_stop by framing this as the force-kill/non-graceful alternative, making the purpose unmistakably 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?

Usage guidance is explicit and actionable: 'Use it to force-kill a container that ignores container_stop, or with signal to poke a process without stopping it... For a normal shutdown prefer container_stop.' It also covers failure modes (conflict error if not running, refusal to signal own container), providing complete when-to-use and when-not-to-use context.

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