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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the safety profile is covered. The description adds real value by disclosing the conditional data-loss behavior ('if it is the last copy, its data goes too') and the interactive approval interruption ('May stop to ask a human to approve'), which the annotations do not convey.

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?

Two short sentences, zero filler, with the destructive consequence and approval possibility front-loaded where an agent will see them.

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, 7-parameter mutation with no output schema and near-zero schema description coverage, the description covers the two most important behaviors (data loss and human approval) but leaves most parameters and any return/confirmation semantics unaddressed.

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 14% (just 'approval'), so the description must compensate and largely does not: project, version, environment, request_key and accept_volume_loss are undocumented in both places. The one nod toward semantics is the approval retry flow ('Send it when calling this tool again after it answered approval_required'), which is already in the schema, and accept_volume_loss is never mentioned despite its obvious relevance to the stated data-loss behavior.

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 (delete) and resource (a Volume's mirror), plus the critical scope condition that data is lost when it is the last copy. This clearly separates it from volume_mirror and volume_remove, 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?

Usage is only implied: an agent infers this is the teardown counterpart to volume_mirror. There is no statement of when to prefer it over alternatives like volume_remove, and no prerequisites beyond the passing mention of human approval.

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