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

Annotations already declare destructiveHint=true, idempotentHint=false and readOnlyHint=false, so the safety profile is covered. The description adds genuinely new context: the blast radius (all subsequent tool dispatch through the manifest is blocked) and a recovery route (fleet__undo). It doesn't mention the dry-run-by-default behavior or the approval requirement, but the core behavioral picture is materially clearer than annotations alone.

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 tight sentences: the action and blast radius come first, the reversibility guarantee second. No filler, no repetition of the title, and the most decision-relevant fact is front-loaded.

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, non-idempotent mutation with no output schema and 40% parameter coverage, the description covers consequences and recovery but leaves key invocation details unaddressed: what a manifest is, that the operation is site-scoped, and when the acknowledgment/approval path applies. An agent can call it, but with avoidable uncertainty.

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 40%, so the description carries the burden of explaining parameters—yet it mentions none of them. 'reason', 'site_id' and 'plugin_slug' are undocumented in both places, and the description doesn't clarify that the target is scoped to one site or what a plugin_slug identifies.

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 ('kill a single manifest') plus the resulting effect ('blocks all subsequent tool dispatch'). The word 'single' implicitly separates it from the sibling fleet__kill_manifests_by_plugin, but that sibling is never named, so the differentiation is inferred rather than 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?

The description gives a lifecycle context ('until cleared') and points to fleet__undo as the reversal path, which helps an agent understand recovery. However, it never says when to choose this over fleet__kill_manifests_by_plugin or fleet__deny, nor does it state preconditions such as the approval flow implied by the acknowledgment parameter.

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