Designers

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

The description goes far beyond the safety hints provided in the annotations. It details the operational constraints—that it reads markup only—and lists critical capabilities it lacks (contrast, focus order, script-built widgets), giving deep behavioral context.

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 perfectly structured. It front-loads the comprehensive list of checks and immediately concludes with a highly dense, single sentence outlining critical limitations, maximizing informational density with zero waste.

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 that no output schema is provided, the description is maximally complete by exhaustively detailing what the tool *does* check and, equally important, what it *cannot* check. This covers all necessary context for the agent to call it correctly.

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 100%, so the schema adequately defines the parameters. The description does not add specific semantic meaning to the parameters (url, html, compareUrl) beyond what the well-defined schema already provides.

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 verb ('Audit'), the resource ('page's static HTML'), and the exact scope (naming the WCAG 2.2 criterion for multiple specific failures). This clearly distinguishes it from a site-level audit.

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 provides excellent usage guidance by explicitly defining the tool's boundaries and limitations. The note 'It reads markup only and cannot test contrast, focus order or script-built widgets' tells the agent exactly when this tool is inappropriate and directs it toward alternatives like 'check_contrast'.

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

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

Beyond the standard safety hints in annotations, the description provides crucial operational constraints, detailing usage limits ('Free up to about 30 colours; Pro takes 200') and the exact output format ('Returns a markdown report'). These are valuable behavioral details.

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 highly dense and efficient, front-loading the core function and following immediately with the detailed process, metrics, and constraints. Every phrase contributes necessary information to the agent.

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 complexity of the task (multi-criterion comparison, specific outcomes like 'nearest passing colour' and 'colors that merge under colour blindness'), the description is highly complete. It covers the input format, the testing methodology, usage constraints, and the output type without relying on an output schema.

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?

With 100% schema coverage, the description's role is secondary, but it still adds significant semantic value by clarifying the *nature* of the required input—specifying that 'tokens' must be in formats like 'CSS custom properties' or 'W3C design tokens,' guiding the agent on the expected content type.

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 purpose is stated with extreme specificity, focusing on testing 'foreground-like token against every background-like token.' This immediately differentiates it from general contrast checks by targeting design tokens and defining the precise methodology (4.5:1 and 3:1 ratios).

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 functions as a strong guideline by explicitly defining the required input format: 'design token file (CSS custom properties... or W3C design tokens).' This tells the agent exactly when to use this specialized tool, contrasting it implicitly with general tools that might take rendered images.

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

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.