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

Annotations already declare readOnlyHint=false and destructiveHint=false, so the safety profile is largely covered; the description's real addition is the authorization constraint. It omits other behaviorally important facts for a mutation: whether restore fails when the document is not archived, whether it bumps the version, and whether 'reason' is surfaced in an audit trail.

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?

One front-loaded sentence with zero filler, and the permission constraint is placed where it is immediately visible. It is arguably too terse for a four-parameter mutation, but nothing in it 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?

An output schema exists, so return values need not be explained, but for a state-changing tool with 25% schema coverage the description should explain expected_version conflict semantics and the role of reason. As written, an agent knows what the call does but not enough to call it correctly on the first attempt or to recover from a version conflict.

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 only 25% — only idempotency_key is documented in the schema — so the description carries the burden and does not compensate. It adds no meaning for doc_key, reason, or expected_version (the latter clearly implying optimistic-concurrency conflict handling that an agent needs to understand), leaving three of four parameters semantically opaque.

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?

Names a specific verb and resource ('Restore a previously archived document'), which lets an agent distinguish it from siblings like archive_document, supersede_document, or rename_document. It stops short of explicitly naming the counterpart operation or stating what state the document returns to, so it is clear but not maximally differentiating.

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?

The parenthetical '(creator or commander only)' is a genuinely useful precondition that tells the agent who can call it. However, there is no guidance on when to restore versus alternatives such as supersede_document or upsert_shared_doc, nor what to do if the document is not currently archived.

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