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

Annotations already declare readOnly/openWorld/idempotent, and the description adds substantial context beyond them: no headless browser is used, Navigation/ads/share bars/comments are stripped, JSON-LD articleBody is preferred when fuller, the fetch is SSRF-safe, and pricing is $0.01 USDC per successful call. Disclosing 'per successful call' pricing and the SSRF protection are exactly the kind of traits structured fields cannot carry.

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?

Purpose is front-loaded in the first clause, with return fields, stripping behavior, and the pricing/endpoint note following in a sensible order. It is dense but nearly every clause is load-bearing; the long enumerated return-field list is the only mild bloat, defensible since no output schema exists.

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?

There is no output schema, and the description compensates by enumerating the returned fields (body text, title, byline, site name, dates, language, excerpt, lead image, word count, reading time). Combined with the stripping rules, JSON-LD fallback, SSRF note, and pricing, an agent has everything needed to call it and interpret the result correctly.

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% (url, maxChars range and default, paragraphs flag), so the schema carries all parameter meaning. The description adds nothing parameter-specific — no mention of maxChars truncation behavior or when to set paragraphs — so the baseline 3 applies.

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?

Opens with a precise verb+resource ('Extract the main article from a web page') and adds the mechanism (Readability-style scoring, no headless browser), which tells an agent exactly what class of output to expect. It implicitly differentiates from siblings like html_to_markdown or web_to_text by promising 'main article' rather than full-page conversion, but never names those alternatives explicitly.

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 conveys an implied use case (article pages, with nav/ads/comments stripped) and gives a practical access route via HTTPS for non-MCP clients. However, it never states when NOT to use it — e.g., that web_to_text or html_to_markdown is preferable for non-article pages — so the agent must infer the boundary with siblings on its own.

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