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

Annotations only declare destructiveHint=true/readOnlyHint=false; the description goes well beyond by disclosing that deletion is permanent, the permission model (logger or project owner), and the confirm-gated preview behavior. These are exactly the behavioral traits an agent needs before invoking a destructive tool.

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 tight sentences with no filler; the destructive scope is front-loaded, followed by permissions and then the confirm gate. Every sentence carries distinct, actionable information.

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 adequately covers destructiveness, permissions, and the confirm/preview flow. It leaves minor gaps such as error behavior when the expense is already on an invoice or whether related data is affected.

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% and both parameters are documented there, so the baseline is 3. The description restates the confirm:true requirement and the preview semantics, which mirrors rather than extends the schema's own wording.

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 (permanently deletes) and resource (an expense), plus a scoping precondition (not yet on an invoice) that separates it from update_expense and list_expenses. An agent can identify the operation and its domain constraint without opening the schema.

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?

Gives clear when-to-use conditions: only for expenses not yet on an invoice, and only by the person who logged it or the project owner. It stops short of naming an explicit alternative (e.g., remove from invoice first, or update_expense), so it is clear context rather than full routing guidance.

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