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

Beyond the safety hints provided by annotations, the description discloses critical operational behavior. Specifically, it defines what the tool returns (signals, prompts, severity) and, crucially, includes the behavioral constraint: 'a human evaluation is still required.'

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 definition is exceptionally dense and efficient. It front-loads the purpose and then details the mechanics (inputs, outputs, warnings) without any filler or unnecessary preamble.

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?

Since no output schema is provided, the description fully compensates by detailing the comprehensive output structure, including 'keyword and markup signals found or missing, review prompts, and blanks for findings and 0 to 4 severity.' This makes the definition functionally complete.

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?

Although the input schema is 100% covered, the description adds important domain context. It specifies the required format options (text, HTML, URL) and gives a concrete example of the content expected for the 'task' parameter, making the inputs more meaningful to 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 is highly specific, stating the goal is to 'Build a Nielsen ten-heuristics review worksheet.' It clearly defines the output structure (signals, prompts, severity) and the resource it operates on (screen or flow).

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?

It clearly guides the user on acceptable input modalities ('text', 'html', or 'url') and gives a concrete example for the 'task' parameter. While it doesn't explicitly compare itself to every sibling, its focus on Nielsen heuristics provides strong differentiation.

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