Run a named scenario

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

With no annotations, the description carries the full burden, and it does disclose one important trait: 'Steps are never invented, repaired, or retried' — so a failing step aborts rather than being silently recovered. It also states where runs are stored. Missing are permission requirements, timeout/failure semantics, what happens to a partially completed run, and what the caller receives back.

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?

One tight sentence with the core behavior front-loaded and the important constraint (no invention/repair/retry) placed last for emphasis. Nothing is wasted.

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?

This is a complex, nested-step composite tool with no annotations and no output schema, yet the description says nothing about what a run returns, how to reference captured frames afterward (diff/baselines), or failure behavior beyond 'no retry'. For this complexity level it is under-specified.

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 description coverage is only 20%, so the description should compensate, but it covers just url and steps generically. It never explains width/height, timeout_ms, selector, the action enum, or that `name` keys baselines — the sole field the schema itself annotates.

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 states a specific compound action: open a URL, execute supplied steps, capture frames, and persist a run under qa/runs/<run_id>. That is concrete and distinguishable from atomic primitives, but it never names the sibling tools (act, capture, diff) it relates to, leaving the differentiation to inference.

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?

There is no when-to-use or when-not-to-use language. An agent must guess whether to drive a flow with scenario_run or compose it from act/capture/wait_for; the description offers no routing signal, prerequisites, or exclusions.

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