inject_init_script

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

No annotations are provided, so the description carries the full burden. It discloses the main persistent behavior (runs before every page load), but omits lifecycle details such as whether the injection applies to the current page immediately, whether it stacks across calls, and how to remove it.

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?

A single, front-loaded sentence communicates action, target, and timing with no filler. Every word earns its place.

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?

For a one-parameter tool with no output schema and no nested objects, this description plus the schema is sufficient for an agent to select and invoke it correctly. The missing lifecycle details lower the score slightly but do not block correct usage.

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?

The schema already documents 'script' as JavaScript code to inject, so the baseline is 3. The description adds meaningful temporal context: the supplied code will be executed before every page load, not just injected and forgotten.

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 uses a specific verb ('inject') and resource ('script that runs before every page load'), clearly conveying a persistent page-load hook. This distinguishes it from one-shot execution tools like evaluate, which run in the current page only.

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 phrase 'before every page load' implies the intended use case: install setup code that should execute on each navigation or reload. However, it does not explicitly state when to prefer this over evaluate or other script tools, nor give exclusions or cleanup guidance.

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