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

Annotations already declare read-only, idempotent, open-world and non-destructive, and the description goes well beyond them by disclosing hard operating limits: 8 s timeout, 5 redirects, 768 KiB remote body, 150k output characters. It also states the no-JavaScript constraint and that native text/markdown is preserved rather than re-converted — exactly the behavioral context annotations 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?

Four short sentences, front-loaded with purpose then usage then caveat then limits — no redundancy with the title, and every clause (JS, native markdown, limits) earns its place by answering a foreseeable agent question.

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 two-parameter fetcher with an output schema and full safety annotations, the description covers the remaining risk surface: client-side rendering, redirect/timeout ceilings, body size, and output truncation. Nothing an agent needs to call it safely and interpret results is missing.

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 50%: url is documented in-schema while max_chars relies on min/max/default only. The description compensates by tying the 150k output-character ceiling to the tool's truncation behavior, giving the agent a reason to set max_chars rather than accept the 100k default. It still doesn't explain what happens at truncation (silent cut vs. marker), keeping it below a 5.

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 ('Fetches one public HTTP/HTTPS page') plus the exact output ('primary readable content as Markdown'). The phrase 'one public HTTP/HTTPS page' implicitly separates it from html_to_markdown (which converts supplied markup) and from multi-page crawlers, so an agent can place it correctly among its siblings.

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?

'Use this for article or documentation body text without page chrome' gives a clear positive condition, and 'It does not run JavaScript; use a browser tool for client-rendered pages' gives an explicit exclusion with a redirect target. It stops short of naming the sibling converters (html_to_markdown, extract_links) that an agent might otherwise confuse it with, so routing is inferred rather than stated.

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