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

Annotations already declare readOnlyHint=true and openWorldHint=true, covering the safety profile. The description does not add behavioral context beyond what the schema provides (e.g., that it waits for CSS selectors or can scroll for dynamic content). It does not contradict annotations, and the minimal description is acceptable because annotations carry much of the burden. However, it does not disclose potential failure modes or return format, keeping it at a 3.

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 two sentences with zero wasted words. The primary purpose is stated first, and the second sentence reinforces the inputs. It is highly concise and well-structured for quick scanning.

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 schema fully documents parameters, and annotations cover safety, so the description does not need to repeat those. However, there is no output schema, and the description does not hint at what the return value looks like (e.g., structured JSON matching the fields). For a tool with arbitrary URL fetching (openWorldHint), potential errors or limitations are not mentioned. This leaves some gaps for an agent, making it slightly below complete.

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 documentation coverage is 100%, so all parameters (url, schema, waitFor, scanFullPage) already have descriptions. The description adds no new meaning about parameters beyond what the schema provides, so the baseline of 3 is appropriate. It does not compensate for any gaps because there are none.

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 states the tool extracts structured fields from a web page using a CSS selector schema. It names the verb (extract), the resource (web page), and the mechanism (CSS selector schema), making it distinct from sibling tools like web_crawl_run or web_markdown_generate. However, it does not explicitly name any sibling it is not, so it falls 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?

The description implies its usage (extract structured data from a single URL) but does not explicitly state when to use it vs. alternatives. There is no mention of when not to use it or what other tools might be preferable (e.g., web_crawl_run for crawling multiple pages). The context of the name and description gives some guidance, so it is not a 2, but it lacks explicit routing.

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