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

Annotations already declare destructive and idempotent behavior, but the description adds valuable context beyond those flags: exactly what is terminated, the lease scoping, and the billing-relevant guarantee that closing never creates another payment. This is concrete operational disclosure an agent can act on.

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?

Two short sentences with no filler: the first puts the action and scope first, and the second adds the payment-relevant guarantee. Every clause contributes something meaningful.

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 one-parameter mutating tool, the definition is nearly complete: the output schema covers return shape, annotations cover idempotency and destructiveness, and the description explains the target and billing side-effect. The only gap is explicit guidance on where session_id comes from, although 'one lease' plus the brs_ pattern provides enough grounding.

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?

Input schema coverage is 0% and the schema provides only the pattern and required flag for session_id. The description never explains what session_id represents, how it is obtained, or how it maps to a browser-session lease, so it does not compensate for the missing schema documentation.

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 uses a specific verb ('terminate') and resource ('the CDP relay and upstream browser') scoped to 'one lease', making the tool's action unambiguous. It distinguishes itself from sibling browser tools like connect and status by focusing on termination and idempotent closing.

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 intended use is implied by the wording 'terminate ... for one lease' and the reassurance about payments, but the description never explicitly states when to use this tool instead of an alternative. There are no exclusions or sibling comparisons beyond what the name already communicates.

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