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

Annotations already declare readOnlyHint and openWorldHint, and the description adds real value on top: a per-call cost of 15 points (a rate/quota constraint an agent must budget for) and the fact that boilerplate is removed from the output. With no output schema, it also names the shape of the return payload, which the structured fields do not cover. It stops short of covering failure modes — JS-rendered pages, unreachable URLs, or what happens when the body is truncated by max_chars.

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 core capability is front-loaded in the first sentence, but the description then says the same thing twice — once in English and once in Korean — plus a separate usage sentence and a bracketed price tag. The duplication costs tokens without adding information for a single reader.

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?

With three well-described parameters and no output schema, the description adequately covers what comes back and what it costs. For an open-world fetch tool, though, it is silent on the things most likely to make a call fail or mislead — dynamic pages, blocked or non-HTML URLs, and whether truncation signals incompleteness.

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%, so every parameter including the format values and the max_chars default is already documented in structured data; baseline 3 applies. The description restates only that output can be Markdown or JSON, adding no syntax, defaults, or trade-off guidance beyond 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?

States a specific verb and resource — extracts a web page's main content as clean Markdown plus structured JSON with named sub-structures (headings, links, images, plain text). It also scopes the extraction ('strips menus, ads, footnotes'), which implicitly separates it from raw-fetch siblings like url_html. It never names a sibling outright, so differentiation is inferential rather than explicit.

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?

Gives one positive use case ('document cleanup, building RAG inputs') but no exclusions and no alternatives. An agent choosing among url_html, url_screenshot, url_similarity, and web_capture_extract gets no guidance on which to pick, even though the distinction (clean text vs raw HTML vs screenshot) is the crux of the choice.

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