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

Annotations already declare destructiveHint=true and idempotentHint=true, but the description adds what the annotation cannot: that the effect is retroactive on existing manifests, that a confirmation phrase gates real runs, and that recovery is per-site via fleet__undo. It does not discuss partial failures across sites or permission requirements, so it is not a full 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?

Three sentences, scope first, then the approval gate, then the escape hatch — well front-loaded with no filler. The compressed phrasing "for real-run" is slightly telegraphic, which keeps it just below a 5.

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 6-parameter destructive fleet-wide operation with no output schema, the description covers the essentials: scope, the approval gate, and reversibility. Missing details like behavior on partial success across sites and what a preview returns keep it from being 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?

Schema coverage is 67%, with dry_run, site_ids, and acknowledgment already documented in the schema. The description confirms plugin_slug is the match key and that the tool spans all sites when unrestricted, but adds no format, default, or interaction detail beyond what is already structured — appropriate baseline 3.

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?

"Agency-wide bulk kill: retroactively disable every manifest matching a plugin_slug across all sites" gives a specific verb (disable), a specific resource (manifests matching a slug), and an explicit scope (all sites). The phrase "every manifest ... across all sites" implicitly separates it from the singular fleet__kill_manifest sibling, so an agent can pick correctly without opening either schema.

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?

It names the preconditions for a real run (an acknowledgment phrase) and points to fleet__undo for per-site recovery, which is the key operational context for a destructive tool. It stops short of explicitly telling the agent to preview with a dry_run first or directly naming fleet__kill_manifest as the narrower alternative, so it stops at 4.

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