delete_statement

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

With no annotations, the description carries the full burden. It usefully discloses that the delete is soft (recoverable rather than destructive) and that is restricted to DRAFT statements, which is meaningful behavioral context. It still omits permissions required, post-delete state, and the return shape.

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 zero waste: the operation and its precondition come first, then the confirmation requirement. Nothing extraneous.

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 single-parameter, no-output-schema tool, the definition covers the operation, its scope restriction, and the user-confirmation step. The remaining gaps (post-delete recoverability path, error conditions for non-DRAFT ids) are minor.

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?

Only one parameter, and schema description coverage is 100% – the schema already documents the id and its DRAFT-only constraint. The description restates that constraint rather than adding format or validation detail beyond the schema, so baseline 3 applies.

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 ('soft-delete') and resource ('DRAFT customer statement'), with the scope constraint (DRAFT only) front-loaded. It distinguishes itself from hard-delete siblings by naming the soft-delete behavior, though it does not explicitly compare against void-style siblings such as void_bill.

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?

'Confirm with the user first' gives one actionable precondition, and the DRAFT-only framing implies when the tool is valid. However, no alternatives are named (e.g., what to do for a posted/reconciled statement), so the agent must infer the escape path.

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