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

Annotations only mark it destructive/non-read-only; the description adds substantial behavior: unpinned entities created by the import are deleted while entities since used are retained and counted, three specific refusal cases, and a dry-run preview when confirm is absent. This is real disclosure beyond the annotations.

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 dense sentences that front-load the action and its side effects, then the failure modes and the confirm requirement. No filler, no repetition of the title.

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 no output schema, the description covers what is deleted versus kept, what the result reports, the dry-run behavior, and every refusal condition an agent needs before invoking it.

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% and both parameters are already documented in the schema, including the non-true confirm behavior. The description reinforces the confirm preview semantics but adds no extra syntax or format detail beyond the schema, so the 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?

Specific verb (deletes/takes back) and resource (a time import and the entities it created), with the exact scope of what is removed versus retained. It is clearly distinguishable from delete_time_entry (single entry) and preview_time_import (read-only preview).

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 explicit refusal conditions (already invoiced, already undone, sample project) and the confirm flag requirement, which effectively tells the agent when the call will fail. It stops short of naming a sibling alternative such as preview_time_import for the no-confirm case.

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