evaluate_script

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

The annotations declare readOnlyHint: false, and the description doesn't contradict this — no annotation contradiction. However, the description adds minimal behavioral disclosure beyond the schema; the rich details (sandbox realm semantics, saveTo path resolution) live in the parameter docs, not the description. For a tool that executes arbitrary JS, a note about side-effect potential or that results may not be serializable would have elevated this further.

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?

Three sentences, each earning its place: what it does, when to prefer it, what to use instead. Front-loaded with the core purpose and zero filler. This is a model of concise, high-information density.

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 complex JS execution tool with 6 parameters and no output schema, the description plus annotations plus rich schema documentation provide a complete picture. The only gap is that it doesn't address error behavior or serialization limits of return values, but these are minor given the strength of the supporting schema docs.

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 100%, and the schema's parameter docs are genuinely rich (saveTo explains string/directory/true behavior, sandbox explains realm isolation and persistence, timeout documents its 5000ms default). Per the calibration baseline, when the schema handles the documentation burden, a 3 is appropriate. The description wisely avoids restating what the schema covers.

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 opens with 'Run a JS function in the page and return its result' — a specific verb+resource+outcome statement. It also distinguishes itself from siblings by naming take_snapshot and the UID interaction tools. The tool's purpose is instantly clear.

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?

Explicit when-to-use guidance: 'Prefer this for targeted reads (a value, text, computed style, whether an element exists) instead of a full take_snapshot.' It also tells the agent what NOT to use it for: 'Use the UID interaction tools for clicking, typing, and filling.' This is textbook usage guidance with named alternatives.

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