Preview a local file in AI Coach

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

The description goes well beyond annotations by disclosing that HTML is rendered with scripts removed, there is no network access, the file is read only by the app, and contents/image bytes are never returned to the model. This is critical behavioral and privacy information the agent cannot infer from the annotations alone.

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?

Three sentences with the purpose front-loaded. Each sentence contributes a distinct piece of information: what it does, safety behavior, and when to use it. The extension list is slightly redundant with schema but not excessive.

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 one required parameter, full schema coverage, an output schema, and clear annotations, the description provides all necessary operational context: purpose, allowed file types, HTML sandboxing, privacy guarantees, and usage boundaries.

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%, and each parameter already has a meaningful description. The description mostly repeats the allowed extension list from the path parameter, adding no significant new parameter-level meaning, so the baseline 3 applies.

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 first sentence states a specific action and resource: 'Open a safe local preview beside the AI Coach mascot.' The allowed-file list and HTML sandbox details distinguish it clearly from sibling tools like show_ai_coach_message or open_ai_coach_dashboard.

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 final sentence gives an explicit usage constraint: 'Use this only for a file the user asked to preview or a file created in the current task.' It also restricts by allowed file extensions. It does not name an alternative sibling, so it falls just short of full routing guidance.

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