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

Annotations already mark this as destructive and not read-only, but the description adds substantial behavior: body restored byte-for-byte, front matter re-serialized without archive markers, refusal when a live file exists, and write-tier approval semantics. There is no contradiction between the description and 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?

The description is organized into three purposeful sections: core behavior, routing, and approval/operator guidance. Every sentence carries operational weight, with no filler or repetition of schema details.

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?

The description covers intent, routing, approval flow, failure conditions, and exact restoration semantics, which is almost everything needed to invoke correctly. With no output schema, a small gap remains: it does not describe the success response or confirmation the agent should expect.

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 slug and companyId are already documented with examples and constraints. The description reinforces the 'no _archived/ prefix' rule but does not add substantially new parameter-level meaning beyond the schema.

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 specific verb ('restore'), a specific resource ('archived knowledge file'), and the target location ('back where it was'). It also explicitly frames the tool as the inverse of delete_knowledge and names the routing alternative save_knowledge, making sibling differentiation clear.

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 gives explicit when-to-use conditions: operator asks to restore/un-archive, or a document read by a fixed path was archived by mistake. It also routes new writes to save_knowledge and notes that the tool is operator-only and refuses when a live file exists.

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