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 disclose two valuable behaviors: it waits for the page to settle, and it returns the page's listing. It omits error behavior (invalid URL, navigation failure), whether history is affected, and any timeout or permission constraints — meaningful gaps for a browser control tool.

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?

A single sentence that front-loads the primary action (load a URL) before the secondary modes, with no filler. It is slightly run-on, packing navigation, waiting, and return value into one clause chain, but nothing is wasted.

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 tool with no output schema and no annotations, the description covers the main action, the alternative modes, the post-condition (waits for settle), and the return shape ('its listing'). The main residual gap is the all-optional parameter case — what a bare call does — which the description leaves ambiguous.

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%: the action enum is documented only as 'Instead of a URL,' and url has no schema description at all. The prose does clarify the semantics — url loads into the selected tab, action values are back/forward/reload, and the two are mutually exclusive — which adds real meaning, but it never states what the default is when both are omitted, despite zero required parameters.

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 gives specific verbs and resource targets: loads a URL in the selected tab, or performs back/forward/reload navigation. This is clearly distinct from click/type/observe siblings, though it does not explicitly contrast itself with fetch or browser_open, which an agent could reasonably confuse with it.

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?

Usage is implied rather than stated: 'in the selected tab' signals that tab_select should come first, and the URL-or-action split hints at the two modes. There is no explicit when-to-use-this-vs-fetch/browser_open guidance and no statement of what happens when both or neither parameter is supplied.

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