evaluate

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

The description discloses meaningful behavioral details: execution happens in the extension isolated world, it is async-aware, and the query mode avoids eval for CSP-proof reads. With no annotations provided, however, the description does not cover side effects, return value serialization, or error behavior, so it only partially carries the behavioral burden.

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 a single information-dense sentence with the core action front-loaded and the two modes clearly separated by 'OR'. It earns a high score for efficiency, though the apparent truncation after 'ex...' keeps it from being fully polished.

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 tool with no output schema, no annotations, and a rich nested query parameter, the description leaves out important operational details such as return format, whether script and query are mutually exclusive, and what happens on execution errors. It provides enough to start, but not enough for an agent to invoke it confidently in all intended scenarios.

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 description adds meaning by framing 'script' as eval mode and 'query' as no-eval reads, which helps disambiguate the two top-level parameters. But schema coverage is only 50% and many nested query sub-properties (all, text, state, inputs, maxLen) are not explained in the description or schema. It partially compensates but not fully.

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 names a specific action ('Run JS on the page') and explicitly identifies a second mode ('CSP-proof no-eval reads via query'). This makes the tool's dual purpose clear and distinguishes it from simpler read/inspect siblings. Even though the text appears truncated, the core purpose is unambiguous.

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 two usage contexts: arbitrary JS execution and no-eval query-based reads for CSP-constrained pages. However, it does not explicitly say when to prefer evaluate over siblings like read, inspect, or explore_page, nor does it state when not to use the tool. The guidance is implicit rather than actionable.

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