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

Beyond destructiveHint=true, it discloses concrete consequences: the Service stays down until the next deploy, a mirror's copy loses writes after its last sync, and the call may block on human approval. That is real behavioral context an annotation cannot convey, though irreversibility and failure modes are not fully spelled out.

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?

Four short sentences, front-loaded with the core action before the constraints and side effects. Dense with no filler, though the first sentence's phrasing ('Make server from's copy a Volume's writer') is slightly tangled.

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 7 params and no output schema, the description covers the semantic risk well but leaves the operational params (wait_seconds, request_key, project/environment scoping) undocumented. An agent would know the intent but not how to drive the call on retry or timeout.

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 14% – just the `approval` param is documented in the schema, and the description only touches `from` (must hold the only copy) and `volume` in passing. project, environment, request_key (looks like an idempotency key), and wait_seconds are left entirely unexplained despite the low coverage requiring the description to compensate.

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?

States a specific verb and resource: promote server `from`'s copy to be the Volume's writer, gated on no server currently holding that role. It is distinguishable from siblings like volume_mirror/volume_release by the 'when no server has one' scoping, though it never names those siblings explicitly.

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 precondition 'when no server has one' and the constraint 'from must hold the only copy' imply when the tool applies. However, there is no explicit routing versus alternatives (volume_release, volume_mirror, volume_move) and no stated when-not case beyond the implicit precondition.

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