safari_run_script

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

No annotations are provided, so the description must carry the burden. It mentions sequential execution but omits error handling behavior (e.g., does a failure stop all steps?), atomicity, or side effects. Some transparency is offered through the step structure, but gaps remain.

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 extremely concise with two sentences that front-load the core purpose. Every sentence provides necessary information without redundancy.

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 tool's simplicity (single parameter, no output schema), the description covers the main aspects: batching, step structure, and action naming. However, it could mention the return value (e.g., results of each step) or default behavior for a more complete picture.

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% for the 'steps' parameter, but the description adds essential meaning by clarifying that action names correspond to other safari_* tools without a prefix. This helps the agent know valid values beyond the schema's generic examples.

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 explicitly states the tool batches multiple Safari actions in one call and specifies the input structure (steps with action and args). It clearly distinguishes from individual sibling tools by noting actions match other safari_* names without prefix.

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 indicates use for batching actions, which implies combining multiple steps, but does not explicitly state when not to use it (e.g., for single actions, use individual tools). Context from sibling tools provides implicit guidance.

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