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

Annotations already declare destructiveHint=true and idempotentHint=true, yet the description adds genuinely new behavioral facts: deletion is permanent, nothing goes to the trash, and tables raise INVALID_TYPE. That goes well beyond the structured hints, though permission requirements or what the response reports on success are not covered.

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 compact sentences with the destructive warning front-loaded and the storage rationale close behind. The trailing INVALID_TYPE note is short and earns its place as an error-prevention hint, though the dense parenthetical about `keep` slightly interrupts the flow.

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, four-parameter tool with an output schema, the description covers the irreversible consequence, the retention rule, the storage motivation, and the main error mode. Return values are handled by the output schema, so nothing an agent needs to invoke this safely is missing.

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 100%, so all four parameters including `keep`, `why`, and `expectedWorkspaceRevision` are already documented in the schema. The description only restates the `keep` default behavior that the schema itself explains, adding no semantics beyond what structured fields provide. Baseline 3 applies.

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 ('permanently delete an artifact's old versions') plus the exact scope (keeps current + newest `keep`). The table sentence hints at what it is not (a rows tool), but the closest sibling, artifact_version_delete, is never named, so the agent must infer that this is the bulk/multi-version variant rather than the single-version delete.

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?

Gives an explicit gating condition ('prune only when your person asks') and a motivation ('frees storage; every version counts toward the owner's storage'). It stops short of naming alternatives, so an agent deciding between this and artifact_version_delete for a one-off removal gets no direct routing advice.

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