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

Annotations already declare openWorldHint=true and destructiveHint=true, so the safety bar is lower, yet the description still adds material context: it is a paid operation ($2 per 1,000 screenshots) with failures free, it performs consent-banner rejection and ad blocking, and it discloses the returned fields. That cost and side-effect profile is precisely what justifies the destructive hint. It does not mention that runs are asynchronous with a 30s default cap, but that is covered in the schema.

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?

Two sentences with almost no waste; the second sentence is dense but information-bearing, packing formats, devices, feature toggles and pricing. The boilerplate first sentence about calling an Actor and retrieving results could be dropped without loss. It is front-loaded with the resource and immediately followed by the concrete outputs.

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 36-parameter, open-world capture tool with an output schema and full schema descriptions, the description covers purpose, output shape, cost model and key behavioral toggles – enough to decide and invoke. The remaining gap is orchestration: it never says the run may return early with a status and nextStep to poll, which is only discoverable by reading the waitSecs parameter.

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% across all 36 parameters, including enums and nested proxy config, so the schema carries the parameter burden. The description itself adds no per-parameter meaning beyond 'full page or viewport, cookie banners rejected, ads blocked, element capture', which merely previews a few settings. Baseline 3 is the correct ceiling here.

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 pairs a specific verb ('calls the Actor ... and retrieves its output results') with a clearly named resource and then enumerates the output form – screenshots in PNG/JPEG/WebP or PDF, plus URL, title, status, size and timings. An agent can tell exactly what it gets back. The opening clause is wrapper boilerplate ('calls the Actor X'), and it never contrasts itself with siblings such as get-dataset-items, so it stops short of a 5.

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?

There is no explicit when-to-use or when-not-to-use guidance in the description body: nothing says to prefer this over fetching raw HTML or over reusing an existing run, and no alternative tools are named. The only routing hint ('follow nextStep to poll via get-actor-run') lives inside the waitSecs parameter description rather than in the tool description, so it does not count toward the top-level guidance.

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