apple_sysinfo

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

With no annotations provided, the description carries full responsibility for behavioral disclosure. It says 'Read' implying non-destructive, but the schema includes a `confirm` parameter that mentions 'protected/destructive action' with no explanation in the description. This discrepancy is not addressed, leaving the agent confused about whether any action could be destructive and what the confirm parameter is for.

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 one sentence plus a list of actions, front-loading the core purpose. It is appropriately sized given the 19 actions, with zero wasted words. The list is necessary to enumerate capabilities and is presented cleanly.

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?

The tool has 2 parameters and no output schema, and the action list in the description provides a high-level overview. However, the `confirm` parameter is not mentioned in the description, leaving a behavioral gap that affects completeness. The enum descriptions in the schema mitigate some incompleteness, but the missing transparency around confirmed actions brings this down.

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%, so the baseline is 3. Every action enum value has a detailed description, and the `confirm` parameter is explained in the schema. The tool description itself adds no extra parameter semantics, but the schema already provides comprehensive information, so no further compensation is needed.

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 'Read macOS system information' with a specific verb and resource, and enumerates all 19 actions. This fully distinguishes it from sibling tools like apple_brightness or apple_music, which target specific apps or features. The purpose is unambiguous.

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 and action list make it clear when to use this tool: whenever macOS system information (battery, disk, CPU, etc.) is needed. While no explicit alternatives are named, no sibling tool overlaps with system information retrieval, so the context is clear. The enum descriptions in the schema further reinforce usage for each action.

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