execute_js

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

With no annotations, the description carries the full transparency burden and meets it richly: it discloses the single total deadline, per-session pinning of all roundtrips, the route-first-then-fallback execution path, no retargeting on fallback, and precise retry semantics ('retries only proven-undelivered work, never an acknowledged script whose side effects may already have run'). These are non-obvious behaviors an agent needs to anticipate how the tool acts at runtime.

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: purpose+deadline, execution mechanism+fallback, and usage guidance+retry semantics. The core action is front-loaded in sentence one, and there is no filler or repetition of schema content.

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 complexity plus an output schema that documents return values and zero annotations, the description covers the essential behavioral surface: deadline, routing, fallback, and retry semantics. The gaps are no_monitor and dialog_policy semantics (especially relevant since arbitrary JS can trigger browser dialogs), which an agent would need to infer from parameter names alone.

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 0%, so the description must compensate. It does add meaning to some params: 'one total deadline' clarifies timeout semantics, 'pins every monitor/retry/result roundtrip to an explicit session' clarifies session_id, and the wait guidance shapes how script should be written. However, no_monitor and dialog_policy receive no explanatory text, leaving their behavior to inference from names and defaults.

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 opening phrase 'Execute arbitrary JS in the requested real-browser tab under one total deadline' names a specific verb, resource, and scope constraint. The fallback detail ('falls back to directed Runtime.evaluate') further differentiates it from raw CDP siblings like cdp_command/cdp_batch, so an agent can disambiguate without opening schemas.

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?

Gives an explicit alternative with a when-not: 'Use wait_for/wait_for_url instead of setTimeout or sleep Promises', which prevents agents from embedding naive waits in scripts. The retry-semantics sentence also guides expectations about side effects. However, it never directly addresses when to prefer execute_js over sibling tools like cdp_command for JS evaluation, leaving some decision-making implicit.

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