Hand control to or from the user

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

Beyond the annotations (readOnlyHint=false, idempotentHint=false), the description discloses key behaviors: the agent stops acting until the user resumes, control genuinely cannot be taken back by the agent, and claim grants a write claim without a snapshot. The note field's untrusted-display nature is covered by the schema, so remaining gaps are minor.

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?

One terse labeled clause per action, action names front-loaded so the agent can scan for its mode, then a closing pointer to browser_status. No filler sentences.

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 stateful handoff tool with no output schema, the description covers the four modes, the pause/resume semantics, and where to check progress. It does not cover edge cases like claiming a tab that already has a snapshot, but is sufficient to call the tool 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?

The schema documents three of four params (75% coverage), but the action enum values themselves carry no schema description – the description supplies their semantics, which is precisely the highest-value parameter information here. It adds meaning well beyond the bare enum list.

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?

Each of the four actions is given a specific, distinct meaning: request_user_takeover asks the user to act and pauses the agent, resume asks the user to hand control back, claim takes a write claim without a snapshot, release drops the claim. An agent can tell exactly what the tool does and distinguishes it from siblings by pointing to browser_status for progress.

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?

It gives concrete when-to-use triggers for request_user_takeover (sign-in, MFA, payment, 'anything you must not do') and clarifies that only the user can perform resume, plus a routing hint to browser_status. It lacks explicit exclusions or a comparison to browser_request_access, so 4 rather than 5.

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