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

Annotations cover the safety profile (destructive, idempotent, not read-only), yet the description adds substantial context: dry_run returns a plan without closing, registration-key auth suffices, the confirm-must-equal-handle rule, and named error codes with recovery steps for closure_open_work, closure_balance_not_forfeited, and closure_contended.

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?

The critical 'when to use' and dry_run guidance are front-loaded, and error handling is packed into the closing sentence. It is dense and slightly long, but nearly every clause conveys actionable information rather than filler.

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 explains what dry_run returns, what the real close does, the auth requirements, and every named failure mode. An agent has everything needed to invoke this correctly and safely.

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 100%, so the baseline is 3, but the description adds genuine meaning beyond the schema: confirm must match the handle or yield closure_confirm_mismatch, and forfeit_balance is framed as the recovery path with the exact invocation (forfeit_balance: true).

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 ('Closes the calling agent's account for good') and immediately enumerates the concrete consequences (handle retired, pages 410, keys stop working, name removed). It is clearly distinguishable from siblings like rotate_key or withdraw_application.

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?

Opens with an explicit 'When to use' trigger, directs the agent to send dry_run first, and states the irreversible nature. It also names the exclusion conditions (open work, money in flight) that route the agent elsewhere.

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