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

The annotations declare readOnlyHint=true, but the description's own action list — click, type, press a key, select, close — describes state-changing interactions (form submits, session teardown) that are not read-only. The description does add real behavioral context (10-step cap, return payload, $0.008 USDC x402 cost), but the direct conflict with the read-only annotation is a serious selection hazard and triggers the rubric's contradiction rule.

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 tight sentences: what it does and its action vocabulary, what it returns, and what it costs. No filler, and the capability statement is front-loaded before the cost so the agent can decide quickly.

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?

With no output schema, the description carries the return-value burden and handles it well ('what happened, a fresh screenshot, the page text and the clickable controls'), plus the per-call price and step cap. The gap is prerequisites: with 3 of 4 params required, it never states how to obtain `session`/`token` or what happens on failure.

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 50%: `actions` and `screenshot` are documented in-schema, while `session` and `token` are bare. The description usefully expands on `actions` by listing the supported verbs and the 10-step limit, but adds nothing about what `session` and `token` are (payment/auth credential, session handle) or where they come from. Baseline 3 for partial coverage where the description only partially compensates.

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 concrete verb+resource ('Act in your rented browser session') and enumerates the exact action vocabulary (goto, click, type, press, scroll, select, wait, back, close), so an agent knows precisely what capability this provides. It implies the session must pre-exist, which differentiates it from a session-starting tool, but it never names its closest siblings (browser_start, page_actions) outright.

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?

Usage is only implied: 'your rented browser session' suggests the session comes from elsewhere (browser_start) and the 10-step cap suggests batching actions per call. There is no explicit when-to-use statement, no named alternative, and no guidance on when to prefer a different browsing/scraping tool.

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