metro

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

With no annotations provided, the description bears full responsibility for disclosing behavioral traits. The single sentence only states the function without mentioning side effects (e.g., starting daemon, modifying runtime), required permissions, or process impacts. This is insufficient for a complex tool.

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?

While concise (one sentence), the description is too brief to be useful. It sacrifices necessary detail for brevity, resulting in under-specification. Important context about the two main actions ('prepare' vs 'reload') is missing.

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 (42 parameters, no output schema, nested objects), the description is severely incomplete. It does not explain return values, required setup, or how the two actions differ. The agent cannot safely invoke this tool based solely on the description.

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 50%, meaning half of parameters lack documented meaning in the schema. The description adds no parameter-level information. For uncovered parameters like 'projectRoot', 'kind', 'publicBaseUrl', the agent has no guidance. The description fails to compensate for the schema gaps.

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 'Prepare Metro runtime or reload React Native apps' clearly states the tool's purpose with specific verbs (prepare/reload) and resources (Metro runtime, React Native apps). It distinguishes from generic sibling tools like 'react-native' but does not explicitly differentiate from other build tools.

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 no guidance on when or when not to use this tool. It lacks context for selecting between this and sibling tools like 'react-native' or 'debug'. No prerequisites or alternatives are mentioned.

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