test_responsive

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

With no annotations, the description carries full burden. It discloses screenshots, optional checks, and custom viewports, but omits side effects: does it navigate the current session? Does it close after? Does it clear state? The project parameter explains shared vs isolated context, but overall behavioral details (e.g., does it modify cookies?) are missing.

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?

Four concise sentences, each adding unique value: action, return value, core benefit, customization. No redundant or extraneous text. Leads with the primary function.

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 no output schema and four parameters, the description covers all parameters and the return type. However, it lacks integration context (does it open a new session? Is it a standalone test?) and details about how checks are performed or how results are structured. Could be more thorough for a complex multi-step tool.

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%, but description adds significant value: lists default viewports, explains project's shared/isolated context, and describes run_checks allowed values. This enriches the schema's minimal descriptions, especially for 'project' and 'viewports'.

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 it loads a URL at multiple viewports, screenshots each, and optionally runs checks. It distinguishes from siblings like 'get_screenshot' (single viewport) and 'set_viewport' (only sets viewport) by emphasizing testing across breakpoints in one call. The verb 'test' implies a testing action beyond just taking screenshots.

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 implies usage for responsive layout testing ('catches layout breakage across breakpoints') but does not explicitly state when to use this tool versus alternatives like 'get_screenshot' for a single viewport or 'run_checks_on_session' for existing sessions. No exclusions or alternative references are provided.

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