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

Annotations already cover the safety profile (readOnlyHint, idempotent, non-destructive), and the description adds substantial context beyond them: ~5s real-browser cost, concurrent text/title fetch at no extra wall-clock, always capturing via preview-{slug}.{rootDomain} which renders the draft or 302s to live. That routing behavior is exactly the kind of non-obvious trait annotations cannot express.

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?

Front-loads the core decision ('genuinely VISUAL') before the returns and latency details, and every sentence carries information. It is dense with em-dash asides and runs slightly long, but nothing is filler.

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?

No output schema exists, yet the description explains what comes back (page text and title alongside the image) and why to read the text. Combined with latency, preview-URL semantics, and the sibling alternative, an agent has everything needed to call this 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 coverage is 75% and the schema descriptions are already detailed for slug, viewport, and full_page, including the mobile-breakpoint rationale. The description's 'pass viewport' and breakpoint-collapse mention largely restate that structured content rather than adding new syntax or constraints, so baseline 3 is appropriate.

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+resource ('Capture a JPEG' of a page) and immediately scopes it to genuinely visual questions, explicitly distinguishing it from read_rendered_page which is name-checked. An agent can tell these two apart without opening either schema.

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 explicit when-to-use criteria (layout, spacing, hierarchy, hero reads as designed, mobile breakpoint collapse) and an explicit when-not ('when the question is only about wording prefer read_rendered_page at ~357ms'). The alternative is named and the selecting condition is quantified with latency.

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