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

Annotations already declare destructiveHint=true, but the description adds critical context: the refund of a free-tier slot and the refusal condition based on closed month snapshots. This goes beyond the annotation by explaining what is destroyed (the built period) and when the operation is blocked, which is valuable for an agent.

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?

Three sentences with high information density: the action, the side-effect, and a key constraint are all included without redundancy. It is front-loaded with the primary purpose and then details constraints, making it easy for an agent to parse quickly.

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 destructive tool with a simple parameter set and no output schema, the description covers essential behavior: what is deleted, the refund, and the refusal condition. It might lack explicit mention of idempotency or partial failures, but annotations already hint at non-idempotency, and the constraints are well-covered, so minor gap.

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 100%, so the baseline is 3. The description does not describe parameters in detail, but the schema descriptions for 'from' and 'to' are clear. The 'currency' parameter's conditional necessity is only in the schema, not the description, but the schema covers it well, so no penalty.

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 states a clear verb ('Delete') and resource ('one built period'), and explicitly distinguishes its side-effect ('give its free-tier slot back') and its scope ('No sibling book is touched'). This uniquely identifies the tool among siblings like ledger_build or month_close.

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 clearly indicates when the tool will refuse (when a closed month's snapshot covers the period) and names the month, which informs an agent of a limitation. However, it does not explicitly contrast with when to use other tools, such as month_close for closing, but the scope statement ('No sibling book is touched') helps differentiate.

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