visual_screenshot_for_humans

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

Annotations indicate readOnlyHint=true, consistent with screenshot capture. The description adds token cost (~1,500 tokens) and save location, which are useful behavioral details beyond annotations. However, the note about 'may return preview+token' is vague and could be clearer.

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 well-structured with sections for wrong/right usage, valid uses, and token cost. It is front-loaded with a clear emoji and purpose. However, the repeated formatting of '❌ WRONG: ...' makes it slightly verbose.

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?

While the description covers many aspects, it does not clearly specify what the tool returns (e.g., file path, success message) beyond 'may return preview+token'. Given no output schema, this is a notable gap for completeness.

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?

Input schema coverage is 100%, and the description adds practical examples like { name: 'login-page', fullPage: true }, helping agents understand parameter usage beyond the schema. This slightly exceeds the baseline of 3.

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 tool's purpose: 'Captures page/element appearance and saves to file.' It also distinguishes from siblings by listing incorrect use cases (alignment, visibility, layout) and directing to appropriate tools, and gives valid use cases.

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 provides explicit wrong usage examples with correct alternatives, and lists valid use cases such as sharing with designers or visual regression testing. This gives clear guidance on when to use this tool versus alternatives.

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