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

Goes well past the annotations by disclosing the session's auth state (a real Chrome signed in as the user), the navigation constraint (only Housecall Pro pages), the ordering requirement (call first), and what the response contains (elements and text in view with the same numbering). That is meaningful context an agent cannot get from readOnlyHint/openWorldHint 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?

Front-loaded with the action and tightly packed, with no filler sentences. Some clauses are compressed to the point of awkwardness ("Answers the page after it: the elements and text in view, with the same numbers"), and the parenthetical aside interrupts the main flow.

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 burden of describing the return value and does so at a high level (visible elements and text with numbering). It leaves two gaps: `url` is not required per the schema, yet the description assumes it is always supplied, and it never mentions the paired close tool or how the session ends.

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?

The schema already documents the single `url` parameter at 100% coverage with a format hint and example. The description adds a real constraint the schema omits: despite the schema implying any public http/https address, only Housecall Pro pages will actually open — a distinction that changes how an agent supplies the argument.

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 and resource — starts the user's Housecall Pro Cloud Browser and opens `url` — plus the key qualifier that it is a real Chrome session signed in as the user. It also separates itself from the API siblings by framing itself as the fallback for what the Housecall Pro tools do not cover.

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?

Strong ordering guidance ("Call it first") and a clear scoping rule ("use it for what the Housecall Pro tools do not cover", "Only Housecall Pro pages open"). However, the closing sentence lists actions it serves — Create job, Create estimate, Create invoice, Send invoice, List customers — which overlap directly with the sibling API tools (create_job, create_estimate, create_customer), muddying rather than clarifying which route an agent should pick.

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