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

Beyond what annotations already declare, the description reveals a non-obvious behavior: the response never includes the credential itself. It also discloses the full return shape and the operational significance of lease status, which is valuable context an agent would not otherwise have.

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?

Each sentence has a distinct job: defining scope, stating an exclusion, giving usage guidance, and providing the return contract. The field list is long but justified because there is no output schema.

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 read-only, idempotent list tool with one fully documented optional parameter and no output schema, the description covers purpose, alternatives, invocation guidance, return fields, and an operational caveat. Nothing needed to invoke it correctly is missing.

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 single optional org parameter is fully documented in the input schema, so the description does not need to add parameter-level detail. The description adds no new parameter semantics, making the baseline score of 3 appropriate.

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 the exact action and object — listing issued temporary-access leases — and describes it as the ledger of who got a short-lived credential against which target and until when. It also explicitly distinguishes itself from list_lease_targets, which shows what can be leased, so an agent can tell them apart immediately.

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 explicitly states when to call this tool: to find a leaseId for revoke_lease, and to check whether a lease has already expired before revoking it. It also names list_lease_targets as the relevant alternative for leasable targets, and adds the practical rule that only status: "active" leases are worth revoking.

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