metro

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It does disclose the binding lifecycle, the 90s timeout, and the override mechanism, which adds value. However, it omits details about side effects, error behavior, or what happens to existing server state, so it is only partially transparent.

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 concise and front-loaded with the core purpose, followed by the key binding rules and timeout. It is efficient with no redundant sentences, though the density of information might require careful reading.

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?

For a tool with 34 parameters, no output schema, and nested objects, the description is incomplete. It does not explain what the tool returns, the difference between 'prepare' and 'reload' beyond names, or how the many parameters interact. An agent would need to inspect the schema for many fields, but even that is insufficient for undocumented ones.

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 44% (low), and the description does not compensate. It only mentions that runtime inputs override the binding, but does not explain the meaning or usage of the many undocumented parameters (e.g., kind, port, bundleUrl, projectRoot). The general note is too vague to help an agent understand which parameters are relevant for each action.

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 the two actions (prepare a React Native development server or reload connected apps) and identifies the resource (the development server bound to the session). It is specific about the verb and resource, though it does not explicitly differentiate from sibling tools like 'react-native' which might overlap, so it loses a point for missing sibling distinction.

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 when to use the tool: it uses the session-bound dev server, and explains how to override the binding with runtime inputs and the binding lifecycle (cleared on session close or fresh open). It does not explicitly mention alternatives or when not to use it, but the context is sufficient for an agent to decide.

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