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

Annotations cover the safety profile (readOnly=false, idempotent=true, destructive=false), and the description adds material context beyond them: exactly what is restored, that files are NOT restored and are permanently gone, and that permission to change tasks is required. This is the kind of disclosure that prevents surprise data loss.

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, front-loaded with the action and its scope; the files caveat and permission note each earn their place. The get_item aside is useful but slightly parenthetical rather than core, keeping it from a perfect 5.

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 mutation tool with no output schema and one undocumented param, the description covers what changes, what is irrecoverably lost, and the authorization requirement. It does not describe the return value or failure modes, which is a minor gap given there is no output schema.

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 0% and the single 'ref' parameter is undocumented, so the description carries the burden. 'By ref' hints that it is a reference identifier distinct from the 'number' also mentioned, but no format or source for the ref is given. Baseline for a minimal one-param schema with no added detail.

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 (restore) + resource (deleted task) plus the scope of what is recovered (number, comments, followers, links). The word 'task' implicitly separates it from the sibling restore_decision/restore_lesson/restore_project tools, so an agent can route without opening any 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 context for when this applies and even a diagnostic hook ('fenbs_get_item on a deleted ref says it is deleted') to confirm the target is deleted. It does not explicitly name the sibling restore tools as alternatives or state when not to use it, so it stops short of a 5.

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