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

Annotations only flag writable/destructive; the description adds real behavioral context the agent could not infer: the Service is down only during the final copy, the old server keeps a mirror during the move, a stopped move resumes on the same call, and execution may pause for human approval. That is substantive disclosure of downtime window, safety, idempotency, and an approval gate.

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 purpose followed by behavior, with no filler. The only blemish is the broken first sentence, which costs a little clarity but not length.

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 complex, destructive migration with no output schema and near-zero schema documentation, the description covers the important runtime behavior (downtime, mirror, resume, approval). It still leaves most of the 7 parameters and the failure/rollback outcome unexplained, so it is adequate but not fully self-sufficient.

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), so the description must carry the rest. It indirectly explains the approval param ('May stop to ask a human to approve') and hints at request_key via resumption, but project, environment, request_key, and wait_seconds are left entirely opaque in both schema and description.

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 verb is inferable ('Put a Volume and the Service using it on server to' = move a volume plus its Service to another server), and it names both the volume and the dependent Service. However, the phrasing is visibly mangled by a template variable ('on server to' where 'to' is the parameter name), and nothing distinguishes it from siblings like volume_mirror or volume_restore. Purpose is recoverable but not cleanly stated.

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?

No guidance on when to prefer this over volume_mirror, volume_restore, or volume_release, and no prerequisites or exclusions. The only actionable hint is implicit idempotency ('If a move stopped, the same call continues it'), which is resumption behavior rather than tool selection.

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