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

Annotations only declare the generic non-readonly/non-destructive profile; the description goes well beyond them by disclosing the reuse-vs-allocate branch, that allocation is metered, the 180-second idle timeout, and that cookies and storage are restored but tabs are not. The idempotency contract around requestId is also flagged, which is exactly the kind of non-obvious trait annotations cannot express.

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?

Four short sentences, each carrying a distinct obligation, with the core behavior front-loaded before the operational warnings. No filler and nothing buried.

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 should ideally say what the return payload contains; the phrase 'the returned browser' hints at it but leaves the shape unspecified. Otherwise, for a two-parameter read-or-allocate operation, the behavioral coverage is sufficient to call it correctly.

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 only 50%, and the sole description is on requestId. The description does clarify that 'label' selects an active browser to reuse, which adds meaning beyond the bare string schema, but it never states whether the label refers to a saved-session name or a browser label, nor what happens on a label mismatch.

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 ('Resume an existing saved session owned by the connected account') and immediately qualifies it with the reuse-or-allocate mechanism, which cleanly separates it from open_browser and get_saved_sessions without needing to name them.

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 an explicit gating condition ('Only call after the user requests resume'), an explicit retry prohibition ('Never retry an ambiguous allocation or change requestId'), and a follow-up obligation ('Close the returned browser when finished'). This is when/when-not guidance no sibling listing could improve on.

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