open_session

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

Annotations declare readOnlyHint=false and openWorldHint=true, but the description adds real substance beyond them: the browser is headless, authentication is supplied by a saved profile, the call returns a session id and page snapshot, and the screenshot flag has a documented default and an ASSERTIFY_SCREENSHOTS=1 override. It does not say whether an existing session is replaced or how many sessions may coexist, which would matter given the multiple session-related siblings.

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 core behavior and return values are front-loaded in the first sentence, with the screenshot detail correctly deferred to a second paragraph. Slightly hurt by the awkward mid-sentence line break and indentation in the screenshot block, which looks like a formatting artifact rather than intentional structure.

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?

No output schema exists, and the description does helpfully states it returns a session id and page snapshot. However, for a session-lifecycle tool with a 0%-covered three-parameter schema, it leaves the url parameter undocumented and omits session semantics (one session at a time? replaces prior? must close before reopening?).

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 0%, so the description must carry parameter meaning, and it only partly does. 'profile' and 'screenshots' are both explained with useful semantics (logged-in-as-saved-profile; default off, env-var override, when to enable), but 'url' — the optional initial navigation target — is never mentioned anywhere.

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 ('Open a headless browser') plus a key distinguishing attribute ('already logged in as the saved profile') and the return values ('session id and page snapshot'). An agent can tell this apart from siblings like close_session, switch_tab, or open_sessions without opening any 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?

The screenshot paragraph gives explicit conditional guidance ('Turn it on when the user wants to watch'), which is genuinely useful. But there is no guidance on when to call open_session itself versus alternatives such as start_login/complete_login or list_profiles, nor on whether a session must be opened before navigate/click. Usage for the core action is only implied.

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