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

With no annotations, the description carries the full burden and does real work: Chromium rendering, no script execution, public-address-only reachability, and a download URL valid for one hour. Missing are failure behaviors (timeouts, unreachable hosts) and any rate-limit or cost note, keeping it at 4 rather than 5.

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 dense sentences, front-loaded with the core action, then behavior, then the return contract. Every sentence adds information an agent needs; nothing is redundant with the title.

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 7-parameter tool with no annotations and no output schema, the description covers the render mode, address restriction, and the return value's lifetime and form, which is what an agent needs to call it correctly. Error handling and rate limits remain unstated.

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 the baseline is 3, but the description adds interpretation: `scale` 2 yields a sharper picture and the choice is between first screen and whole page. That maps the knobs to intent rather than merely restating field names, lifting it above baseline.

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?

States a specific verb and resource — 'Take a picture of the web page at a public http(s) address' — with formats and viewport scope, which distinguishes it from siblings like html_to_image (renders supplied HTML) and get_website_report (produces a report). It stops short of naming the sibling it should not be confused with, so a 4 rather than 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?

Usage constraints are clear: only public http(s) addresses are reachable, and the page is drawn without running its scripts, which tells the agent when this tool will not give the expected result. No explicit alternative tool is named for cases like authenticated pages or JS-rendered content.

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