set_browser

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

Annotations are absent, so the description must carry the full behavioral disclosure. It mentions one behavior: CDP reuses an existing Chrome or Edge session, which is useful. However, it does not disclose any side effects of setting the browser, whether it modifies persistent state, or how it interacts with other tools. This is minimal coverage for a configuration tool.

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 description is very concise, consisting of two short sentences with no superfluous content. It front-loads the primary purpose and adds one specific behavior. However, it is so brief that it omits crucial details, making it efficient but not adequately informative.

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?

For a tool with 4 optional parameters and no output schema, the description is incomplete. It does not explain how the parameters interact, when each mode is appropriate, or what values are expected. The lack of behavioral context beyond the CDP reuse note leaves agents guessing about the full impact of calling this tool.

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 description does not explain any of the four parameters. It loosely refers to 'browser' and 'session connection mode', but does not map these to the schema properties, nor does it clarify the meaning of 'cdpUrl', 'profileDir', or the enum values for 'mode'. With 0% schema description coverage, the description fails to compensate, leaving agents without guidance on how to fill optional fields.

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?

The description clearly states the tool's purpose: to choose a browser and session connection mode. It also adds a specific detail about CDP reusing an already logged-in Chrome or Edge, which helps distinguish it from sibling tools like get_settings or search_hh_vacancies. However, it does not enumerate the exact modes or browser options, leaving that to the 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?

There is no explicit guidance on when to use this tool versus alternatives. The only hint is that CDP reuses a logged-in browser, which indirectly suggests a use case, but it does not explain when to choose 'cdp' vs 'persistent' or when this tool should be called in a workflow. Sibling tools are unrelated, so the absence of routing guidance is notable.

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