Run an npm package script

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

Annotations already mark destructiveHint: true. The description adds that it runs a script, reinforcing mutation, but doesn't elaborate on specific behaviors (e.g., side effects, environment changes). No contradictions, but minimal extra context beyond annotations.

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?

A single sentence of 15 words conveys the core purpose and key constraint (auto-detected or specified root). No redundancy; every word adds value.

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?

With 5 parameters, no output schema, and destructive hint, the description lacks details on return value (e.g., stdout, exit code), error behavior, or environmental setup. This is insufficient for an agent to fully anticipate tool outcomes.

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 40% (only project and cwd described). The description adds context about auto-detection vs explicit root, relating to cwd and project. However, it does not explain script, args, or timeoutSeconds, leaving gaps for the agent.

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 clearly states it runs an npm script from package.json, with auto-detection or explicit root. The verb 'runs' and resource 'script declared in package.json' are specific, and the title further clarifies. This distinguishes it from sibling tools like run_command, run_tests, etc.

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 does not explicitly state when to use this tool vs alternatives like run_command. It implies usage for npm scripts, but lacks explicit guidance on context or exclusions. The name helps, but no direct comparison is made.

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