navigate

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

With no annotations, the description carries the full burden and does so well: it discloses the wait-for-load behavior, redirect handling, the refusal of local/private/internal addresses with an error, and that the page retains the owner's signed-in session. These are non-obvious operational traits an agent needs before calling.

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-loaded with the core action and return value, then constraints, then the parameter note. Every sentence earns its place; nothing is restated 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?

An output schema exists, yet the description still conveniently notes the final URL/title return, and it fully covers the security restrictions and session semantics. Nothing an agent needs to invoke this correctly 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 0%, so the description must compensate for the single url parameter, and it does by specifying the expected format with an example ("https://example.com/account"). That is meaningful added value, though it doesn't cover edge cases like URI encoding or query strings.

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 (Open a URL) and resource (the vault's browser) with the side effect of waiting for load. It clearly distinguishes itself from siblings like read_page and click by describing navigation as its job rather than page interaction.

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?

Explicitly routes the agent: a redirect to a sign-in page means use check_login_wall then request_takeover, naming both alternatives and the triggering condition. It also states the boundary condition that only public websites open, so the agent knows what will fail.

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