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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds genuinely new behavioral facts: a single page load with no interaction, public pages only, and that the screenshot covers the visible viewport rather than the full page. It omits failure modes for blocked/JS-heavy pages and any timing or rate limits.

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?

Two sentences, no waste. The core behavior is front-loaded and the parenthetical examples follow, so the definition remains skimmable while still informative.

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 no output schema, the description correctly carries the burden of describing the return shape, naming both markdown content and a viewport screenshot. Remaining gaps are truncation signaling and error behavior for inaccessible pages, which are minor for a two-parameter read tool.

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%, with url (public http(s), https assumed) and max_chars (100-200000, default 50000) fully documented. The description adds no parameter-level detail beyond confirming the return type is markdown, which only loosely relates to max_chars, so the baseline of 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?

The description uses a concrete verb and resource: it opens a public page once and returns two specific artifacts, markdown content and a screenshot of the visible area. That dual return distinguishes it functionally from read_page and take_screenshot, though it never names those siblings, so an agent must infer the overlap itself.

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?

It gives explicit usage context, 'use it when you need the text and also to see the page,' with concrete examples such as reviewing a landing page or comparing content with design. It never states when not to use it, e.g. text-only work should go to read_page or screenshot-only work to take_screenshot, so routing relies on inference.

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