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

With no annotations, the description carries the full burden and does well: it discloses that stored data is deleted, that the ACL run_finish is checked, that there is no usage-meter spend and no email, and that a signed receipt is returned. It stops short of stating irreversibility or any confirmation/undo behavior, which keeps it from a 5.

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 and its data-destruction semantics, followed by constraints and alternatives. The trailing 'Former name: run_finish' is useful for tool discovery but slightly less essential; otherwise there is no waste.

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?

No output schema exists, but the description names the return value (signed wipe receipt), and with no annotations it covers permissions, side effects, and alternatives. A note on irreversibility or post-conditions would make it fully complete.

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?

The tool takes zero parameters, so the schema-side burden is nil and the baseline is 4. The description correctly does not invent parameter details, and the 'run key' scoping is conveyed through context rather than an input field.

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 ('Wipe every namespace bound to this run key') plus the return artifact (signed wipe receipt), and explicitly scopes it to run keys only. It is clearly distinguishable from siblings like manage_kv and the implicit TTL-based wipeOnExpire.

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 explicit routing rules: use manage_kv action=delete to remove a single key, or let wipeOnExpire clear a run key at TTL. Combined with the constraint 'Valid only for a run key', the agent has clear when-to-use and when-not-to-use guidance.

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