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

The description adds real behavioral context beyond the annotations: the browser is a signed-in Chrome session on Cotlet, only Tradify pages will open, and the tool returns the page state after loading. That return-value note matters because there is no output schema. However, it doesn't say what happens when the URL is non-Tradify or how a session is resumed versus newly launched, and "Starts the browser" brushes against readOnlyHint=true without resolving whether any persistent state changes.

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 ordering instruction and the scope constraint are front-loaded, and the sentences are dense but each carries information. The trailing list of served actions is somewhat expendable, but it usefully signals scope for an agent deciding between this and the native Tradify tools.

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 correctly compensates by describing the response as the elements and text in view with the same numbering used elsewhere. Combined with the session/auth context and the page restriction, an agent has enough to invoke this correctly; only cross-sibling routing against navigate/read is left implicit.

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, but the description genuinely adds meaning the schema lacks: "Only Tradify pages open" narrows the supposedly public http/https URL to Tradify destinations, which is a material correction to the schema example. That's a real semantic contribution rather than a restatement.

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?

"Starts the user's Tradify Cloud Browser ... and opens `url`" gives a concrete verb plus resource, and the parenthetical (real Chrome, signed in as the user) pins down what kind of browser. It distinguishes itself from the native Tradify domain tools by saying "use it for what the Tradify tools do not cover," though it never distinguishes itself from the obvious sibling `cotlet_browser_navigate`.

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?

"Call it first" sets ordering, and "use it for what the Tradify tools do not cover" gives an explicit carve-out versus the create_job/create_quote/create_invoice family. It stops short of exclusions against `cotlet_browser_navigate` or `cotlet_browser_read`, which an agent could easily confuse with this entry point.

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