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

The annotation only marks the tool as destructive. The description adds genuinely useful behavior beyond that: this is a soft delete that writes `deletedAt`, and the application physically purges the record after 14 days. That reversibility window is exactly the context an agent needs before calling a destructive tool. It still omits idempotency and how already-deleted records are handled.

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 description is two tight sentences with no padding, and it front-loads the essential fact: this is a soft delete. Nothing is wasted.

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 destructive mutation with no output schema, the description covers the important lifecycle semantics: writing `deletedAt` and the 14-day purge. It is not complete: error behavior, re-deletion, and return value are unstated. But given the tool's low complexity, what is missing is 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?

The schema has zero description coverage, and the single required parameter `id` is never mentioned. The description does not say whether `id` is the TODO identifier, whether it accepts a soft-deleted record, or what error occurs if it is unknown. With only one parameter, the gap is small but real.

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 uses a concrete verb and resource: it writes `deletedAt` to perform a soft delete. That distinguishes it from hard-delete semantics and from a pure state mutation such as complete_todo. However, it never names a sibling, and it does not explicitly contrast itself with complete_todo or update_todo.

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?

There is no explicit guidance on when to use this tool: not when to prefer complete_todo, nor when to prefer update_todo, nor what a caller should do if the record is already soft-deleted. Usage is only weakly implied by the word 'delete'.

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