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

Adds real context beyond the annotations: the browser is a signed-in real Chrome, the URL is routed to the site's existing tab rather than spawning duplicates, the user's own tabs are preserved, and the tool returns with the same element numbering as later reads. That is meaningful non-obvious side-effect and auth information. It stops short of covering failure/loading behavior (timeouts, unreachable URLs, what happens while the page loads), which is why it is not a 5.

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 lifecycle instruction, then the tab-targeting behavior, then return content, then app-specific routing. Dense and largely waste-free, though the trailing Contractor Foreman action list is a routing aid that sits slightly awkwardly at the end of a tool description.

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 compensates by telling the agent what comes back (visible elements and text). For a two-parameter, zero-required open-the-browser tool, this is nearly complete; only wait/load semantics and the open-vs-navigate boundary are 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 description coverage is 100%, so both `app` and `url` are already documented in the schema, and the description adds only the tab-targeting nuance for `url`. It does not elaborate on the `app` parameter's escape hatch or on URL formatting, so the baseline of 3 applies.

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 — starts the user's Cloud Browser and opens `url` — and clarifies that it is a real Chrome instance where the user is already signed in. It clearly separates itself from interaction siblings by the instruction 'Call it first', but it never distinguishes itself from cotlet_browser_navigate, which an agent could plausibly choose instead.

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 sequencing guidance ('Call it first') and a concrete list of downstream actions in Contractor Foreman (Create estimate, Add daily log, etc.) that signals when this tool is the right entry point. It lacks any when-not guidance and does not name cotlet_browser_navigate or cotlet_browser_tabs as alternatives for moving within an already-open session.

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