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

Annotations already carry readOnlyHint=false, idempotentHint=true, and destructiveHint=true, so the bar is lower. The description adds genuine context beyond those flags: it specifies exactly what gets destroyed ('retained message and attachment content') and the observable side effect ('stop inbound visibility'), and 'idempotently' aligns with the idempotency hint. No contradiction with annotations. Minor gap: permanence/recoverability of the deletion is not stated.

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 16-word sentence, front-loaded with the action ('Idempotently stop... delete...'), with no filler. Every element earns its place: idempotency, the visibility side effect, the destroyed content, and the single-lease scope. The description is appropriately sized for a one-parameter destructive operation.

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?

An output schema exists so return values are documented elsewhere; annotations cover the safety profile (destructive, not read-only, idempotent); the description adds scope and the exact effects of the call. For a 1-parameter delete tool this is nearly complete. The only notable omission is whether the deletion is permanent/recoverable and whether the lease ID becomes invalid afterward.

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 should compensate, but it only ties the parameter to the operation via 'one inbox lease' without explaining how to obtain a valid inbox_id. That said, the single parameter is self-named and tightly constrained by the schema's pattern (^inb_[A-Za-z0-9_-]{22,64}$), so the practical risk of misusing it is low.

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 names a specific verb-resource pair — 'delete... one inbox lease' — and goes beyond a generic delete by stating the concrete effects: 'stop inbound visibility and delete retained message and attachment content.' This clearly differentiates it from the sibling inbox tools (attachment, messages, read, status), which are non-destructive operations on the same lease.

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?

Usage context is implied by the purpose ('when you need to retire a lease and purge its content'), and the idempotency statement signals it is safe to retry. However, there is no explicit when-to-use versus when-not-to-use guidance, no mention of prerequisites, and no pointer to non-destructive alternatives like ausca_agent_inbox_read or ausca_agent_inbox_status.

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