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

Annotations already flag openWorldHint and destructiveHint, so the safety bar is lower; the description still earns credit by disclosing that credentials are never handled by the agent, that a browser window appears on the user's Mac (blocking on human interaction), and that the resulting profile persists locally and is reused by other tools. It does not explain why destructiveHint=true or how to revoke/close the stored profile.

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 short sentences, front-loaded with what happens (real browser, user signs in), then the persistence consequence, then the naming convention and risk note. Every sentence earns its place and nothing is repeated.

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 covers what the agent needs: opening a window, the human-in-the-loop step, and the downstream session reuse. Minor gaps remain — what happens if the user abandons the login, and how sessions are listed or deleted (covered by sibling tools but never referenced).

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% and both parameters are already documented with examples, so the schema does the heavy lifting. The description reinforces the `session` convention ('stable name per site', e.g. 'linkedin'), which is marginally useful but duplicative of the schema text.

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 — opens a real browser window on the Mac so the user signs in themselves — and immediately differentiates itself from the web_navigate/web_read/web_screenshot siblings by explaining that those reuse the saved session. An agent can distinguish this from any other web_* tool without opening a schema.

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 clear triggering context (when a site needs authenticated access, use this once and the session persists for later web_* calls) and a concrete convention for the `session` parameter. It stops short of explicit exclusions, e.g. it never says to use plain web_navigate for anonymous browsing or to call web_session_close/web_session_delete when done.

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