navigate

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

Goes well beyond the annotations: it discloses that the call blocks until load, that DNS/connection errors fail the call, the exact tab-reuse precedence, and what the response contains (interactive element preview with refs, first console errors, failed requests, declared WebMCP tools). None of that is recoverable from readOnlyHint/openWorldHint/idempotentHint alone.

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?

Three sentences, front-loaded with the action and wait semantics, then fallback, then return payload. Dense and mostly waste-free, though the final sentence packs four distinct return elements into one long clause that is harder to parse than it needs to be.

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 carries the return-value burden itself and does so fully — it names the interactive preview, refs usable downstream in click/type_text/hover, console errors, failed requests, and WebMCP tools. An agent has everything needed to call this and use 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 baseline is 3. The description adds the reuse chain including 'or created', which the schema omits — but it also conflicts with the schema, which says the fallback is 'the active one' while the description says it opens a new tab 'rather than taking over the active tab'. That discrepancy needs resolving before an agent can rely on either.

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 (navigate) and resource (a Chrome tab), plus the load-wait behavior and failure modes. It is clearly distinguishable from siblings like create_tab, get_tabs, or wait_for because it names URL navigation and its side effects directly.

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?

Explains the tab_id-omitted path precisely: reuse the session's last tab, else open a new one rather than taking over the active tab. That's strong conditional guidance, but it never names an alternative tool (e.g. create_tab, get_tabs) for agents that want explicit tab selection.

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