navigate

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

With only openWorldHint declared, the description carries the burden well: it specifies the exact result format, that HTTP error statuses are reported rather than thrown, that network failures surface as net::ERR, and the subtle distinction between a committed-but-unsent-settled navigation (not an error, marked "still loading") and a never-committed navigation (error, stopped). That timeout semantics disclosure is exactly the non-obvious behavior an agent needs.

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 primary action is front-loaded and no sentence is filler, but the middle section is a dense run-on that packs return format, error taxonomy, and snapshot options into one long clause chain. A short sentence break would improve scanability without cutting content.

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, yet the description precisely describes the return string format and the viewport snapshot payload, plus the error/still-loading branches. For a 6-parameter navigation tool with minimal annotations, an agent has everything needed to call it and interpret the result.

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 100%, so the baseline is 3; the description adds genuine meaning beyond the schema by stating that a scheme-less URL is upgraded to https and clarifying that snapshot:true attaches the whole page whereas the default attaches a viewport snapshot. Tab, wait_until, and timeout_ms are left to the schema, but that is acceptable given full coverage.

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 specific verb and resources: "Go to a URL (scheme-less gets https://), or back/forward/reload," which matches the action enum exactly. It is clearly distinguishable from siblings like click (which follows links in-page) and snapshot (which only captures).

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 explains the interplay with snapshot ("call snapshot for the whole page; snapshot:false to skip"), giving real routing guidance between this tool and its most confusable sibling. It does not explicitly say when to prefer a click-driven navigation over navigate, so it is strong but not exhaustive.

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