run_benchmark

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

With no annotations, the description explains timing behavior, the async nature via job_id, and the effect of different timeout strategies. Good coverage of behavioral traits, though does not address side effects or destruction.

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 a single paragraph of 4 sentences, reasonably concise. It front-loads the tool identifier and then covers behavior. Could be slightly more structured but is efficient overall.

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 8 parameters with 0% schema descriptions and an output schema (unseen), the description lacks coverage of the command execution aspect (what path and command represent). It does not explain what a benchmark is or how results are returned, leaving gaps for a new user. Acceptable but incomplete.

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 has 0% description coverage, so description must compensate. It explains the purpose of 5 parameters (expected_runtime_seconds, timeout_seconds, check_after_seconds, poll_interval_seconds, on_timeout). However, it ignores path, command, and background, which are critical. Adds meaning for most but misses key ones.

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 implies running a benchmark with explicit timing, but does not explicitly state 'runs a benchmark command'. It mentions 'Kali Agent MCP tool: run_benchmark' which identifies the tool but does not fully clarify the action. Good, not perfect.

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?

Provides clear guidance on choosing on_timeout values for different scenarios: 'continue_background' for long-lived async work returning a job_id, versus 'kill' or 'return_partial' for bounded synchronous work. Does not compare to sibling tools but gives actionable usage advice.

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