run_command

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

With no annotations available, the description carries full responsibility for disclosing behavior. It covers multiple critical constraints: the command runs only fixed argv (no shell, no agent-supplied line), the target must be shell-safe and single-arg, trust requires 'plumb trust' for project configs, it runs under an OS write-jail sandbox, and output/runtime are bounded. This is exemplary transparency beyond what any annotation would provide.

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, front-loaded paragraph that starts with the core purpose, then constraints, then the alternative. It is slightly repetitive with the schema's parameter descriptions (e.g., shell-safe, target placeholder), but the extra context about trust and sandbox justifies its length. It could be trimmed by a sentence, but remains efficient and well-structured.

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 moderate complexity, no annotations, and no output schema, the description is remarkably complete. It addresses how commands are configured, trust requirements, sandboxing, output/runtime bounds, parameter substitution constraints, and the sibling tool alternative. An agent can safely invoke this tool knowing exactly what to expect and what conditions apply.

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 100%, meaning both 'name' and 'target' are already fully documented in the input schema. The description largely repeats the schema's content (e.g., {target} placeholder, shell-safe restriction) rather than adding new parameter semantics. Baseline 3 is appropriate because the schema does the heavy lifting; the description adds no noteworthy nuance beyond it.

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: "Run a named command from the workspace's [[command]] allow-list (build/test/lint/scripts) without leaving plumb." It clearly identifies the tool's scope and immediately distinguishes it from execute_shell_command by framing the allow-list mechanism. This is exactly the kind of precise, differentiating language expected.

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 provides explicit when-to-use guidance and names the alternative: "Use execute_shell_command instead only for an ad-hoc command not worth adding to the allow-list (it must be enabled first)." It also clarifies when trust is required (project config) vs. not (global config), giving the agent a clear decision framework.

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