run_command

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

No annotations are provided, so the description carries the full burden. It discloses a key behavioral trait: build/test commands are refused without an NPU, while read-only commands are unaffected. It also notes destructive patterns are blocked (in the schema). This adds meaningful context beyond the basic purpose, though it doesn't fully detail output or 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 efficiently structured with a one-sentence purpose up front, followed by a second paragraph of specific behavioral constraints. Every sentence earns its place with no filler or repetition.

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 tool's complexity (arbitrary shell command execution) and the existence of an output schema and full parameter schema, the description is quite complete. It covers usage alternatives, key restrictions, and the NPU-specific behavior. It could elaborate slightly on return values, but the output schema mitigates that gap.

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%, so the baseline is 3. The description enriches parameter understanding by clarifying the 'command' parameter's constraints (e.g., refusal of build/test commands under no-NPU conditions) and the 'repo' parameter's cwd behavior. This adds value beyond the schema alone.

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 states a specific verb+resource: 'Run an ad-hoc shell command in a repository.' It clearly distinguishes from siblings by explicitly recommending run_task for known tasks and git_log/git_diff/read_file for read-only operations, establishing this tool as the fallback for arbitrary commands.

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 explicit usage guidance: 'Prefer run_task for known tasks or git_log/git_diff/read_file for read-only operations.' It also warns that build/test commands are refused when no NPU is reachable, giving clear 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.