Tap

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

Annotations confirm read-only safety (readOnlyHint=true), while description adds critical behavioral context: performance implications ('LAST RESORT'), size optimization strategy ('prefer jpeg quality=30'), and explicit guidance that alternatives provide better feedback for non-visual checks.

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?

Perfectly structured: urgent priority marker ('LAST RESORT') front-loaded, followed by ordered alternatives, use-case restriction, and optimization tip. Zero redundancy; every phrase guides selection or usage.

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?

Strong coverage for a 2-parameter tool with no output schema: describes output type (image), covers the primary parameter optimization concern (quality/size), and provides clear selection criteria. Minor gap in not describing return format structure.

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 has 0% description coverage. Description partially compensates by providing concrete semantic guidance ('prefer jpeg quality=30') suggesting optimal parameter values, but does not fully document parameter ranges or the trade-offs between jpeg/png beyond the size hint.

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?

Description opens with specific verb+resource ('Capture the current page as an image') and immediately distinguishes from siblings by restricting usage to 'visual verification (layout, rendering)' versus DOM inspection or state checking.

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?

Exemplary guidance: explicitly labels tool as 'LAST RESORT', lists three specific preferred alternatives (inspect.toasts, tap.eval, inspect.page), and defines the narrow scope ('Only use screenshot for visual verification').

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