Scrape a URL (cost-aware: free first, Bright Data only if blocked)

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

With no annotations provided, the description fully bears the burden of disclosing behavioral traits. It reveals the free-first/fallback-to-paid logic, the in-memory skip-list for hard domains, the types of anti-bot walls detected, and that results report which tier was used and whether credit was spent. This is rich, non-obvious behavior that goes well beyond the schema and helps the agent anticipate side effects like spending.

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 information-dense and well-structured. It opens with the primary positioning ('PREFERRED scraping tool'), then explains the cost optimization strategy, detection criteria, skip-list behavior, cost outcome, and usage alternatives. Every sentence contributes distinct value: strategy, fallback conditions, memory optimization, pricing, output reporting, and alternative tool guidance. No filler or redundancy.

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?

The tool is complex (16 params, no output schema, no annotations), yet the description covers the essential context: cost model, fallback triggers, the skip-list, and result reporting. It also provides comparison to siblings. While it doesn't detail the full return structure or error handling, the schema thoroughly documents parameters, and the description compensates for missing annotations. A slight gap is the lack of mention of what happens on total failure, but overall it is quite complete for the complexity.

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 schema already provides 100% description coverage for all 16 parameters, so the baseline is 3. The description does not directly elaborate on individual parameters but does provide context for the overall cost-aware behavior that some parameters (e.g., free_only, force_bright_data) relate to. It adds no parameter-specific meaning beyond what the schema offers, hence a solid 3.

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 clearly identifies smart_scrape as a scraping tool that fetches a page with a cost-aware strategy, using the cheapest method first and falling back to a paid option only when necessary. It explicitly names sibling tools (unlocker_scrape, browser_scrape) and positions this tool as the preferred read-only fetch tool, distinguishing it from alternatives with different purposes.

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 gives explicit usage guidance: it states this is the preferred scraping tool, recommends using it 'instead of unlocker_scrape for read-only fetches,' and reserves browser_scrape for 'real JS interaction.' It also explains the cost-saving behavior, making clear when the paid tier is triggered, which helps the agent decide when to invoke it.

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