stealth_mode

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

Beyond annotations that only flag readOnly=false, the description discloses concrete behavioral traits: randomized fingerprints, human behavior simulation, WebRTC/canvas spoofing, robots.txt respect on every navigation, one-shot teardown, and credit costs per operation. It also clarifies the side-effect of setting respect_robots to false (recorded against the API key). These add value beyond what annotations convey, though it doesn't cover rate limits or response error shapes.

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 one dense paragraph, but every sentence carries decision-relevant information: when to use, what it does, operation modes, robots handling, cost model, and an example. Some structure (bullets for cost or operation modes) would improve scannability, but there is no filler or repetition.

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 12 parameters, nested objects, multiple operations, and no output schema, the description covers the key contextual elements: the anti-bot problem it solves, the two usage patterns, robots.txt policy, credit cost, and an example. It does not explicitly state what the return payload looks like beyond 'returns the requested formats,' but the schema already describes max_inline_chars, redact_pii, and result_handle, so the missing piece is minor.

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 100%, so parameters are already documented, but the description enriches the operation parameter by explaining the one-shot scrape lifecycle versus the multi-step alternatives and gives a concrete invocation example ('stealth_mode({operation:"scrape", url:"https://example.com", formats:["markdown","links"]})'). It also attaches cost semantics to specific operations (5 credits per browser operation vs 1 for configure/enable/disable/get_stats/cleanup), meaning beyond the raw enum values in the schema.

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 a specific trigger ('when a site blocks normal scraping – Cloudflare, Datadome, or other bot-detection systems') and names the resource and action ('Renders in a Playwright browser... operation:"scrape"'). It also explicitly distinguishes itself from the normal 'scrape' sibling with 'Not a first choice: try scrape first and switch here after a 403/429/CAPTCHA/challenge page or an empty shell.' This gives an agent a precise selection basis.

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?

It provides explicit when-to-use guidance ('Use this when a site blocks normal scraping...'), a clear alternative ('try scrape first'), and the exact failure conditions that justify switching (403/429/CAPTCHA/challenge page or empty shell). It also separates the one-shot scrape path from the multi-step create_context -> create_page -> cleanup sequence, so an agent knows which operations fit single vs repeated work.

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