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

Annotations already declare destructiveHint=true, but the description adds genuinely new behavior: the call is gated on approval from both parents' owners and will return 409 confirmation_required with a confirmation_id until that approval lands. That two-phase, human-in-the-loop protocol is exactly the kind of context annotations cannot convey. It stops short of saying what happens on rejection/expiry or whether the move is atomic.

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 dense sentence with the core action front-loaded, then the confirmation protocol, then the principal restriction. No filler. The telegraphic "People only." is terse but unambiguous; a few more words on the approval sequence would still earn their place.

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, approval-gated mutation with an output schema available, the description covers the safety-critical path (who must approve, what error to expect, that agents are excluded). Remaining gaps are edge-case behavior rather than anything required to call it correctly.

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 only 25% (only idempotency_key is documented in the schema), so the description must carry more weight. It does explain the confirmation_id lifecycle implicitly via the 409/confirmation_required flow, and "subtree inside its tree" maps onto node and new_parent, but neither parameter is defined and the scope rules (e.g., cycles, same-parent no-op) are unstated.

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?

"Move a subtree inside its tree" gives a concrete verb (move) and resource (subtree/tenant) plus the scoping constraint that the operation stays within one tree, which rules out cross-tree relocation. It does not name or contrast with sibling tools like attach_tenant or detach_tenant, which sit adjacent in the tenant-management family.

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?

"People only" is a real eligibility constraint that tells an agent the call will be rejected for agent principals, and the confirmation flow implies a two-step invocation. However, there is no explicit routing guidance such as when to use move_tenant versus detach_tenant + attach_tenant, so an agent must infer the alternative.

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