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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive, so the safety profile is covered. The description adds that each row carries a reason and timestamp and that aggregate counts are returned, which is genuinely useful. It says nothing about ordering, pagination, or volume limits for an agency-wide listing.

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?

A single front-loaded sentence packing scope, per-row contents, and returned aggregates with no filler. Every clause earns its place.

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?

With no output schema, the early mention of reason/timestamp and total_active/total_killed counts is the right instinct and partly fills that void. However, an undocumented plugin_slug filter and no pagination or result-size guidance leave gaps for an agency-wide listing tool.

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 50%: site_ids is documented in-schema while plugin_slug has no description anywhere. The description adds no parameter meaning at all, so it neither compensates for the gap nor clarifies the default 'every eligible site' scope. Baseline 3 applies since the description is silent but the schema covers half.

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 ('List') and resource ('currently-killed manifests in the agency') plus what is returned (reason, timestamp, active/killed counts). The title's 'switched-off plugins' disambiguates the jargon. It does not explicitly name the counterpart mutators (fleet__kill_manifest, fleet__restore_from_snapshot), so sibling differentiation is only implicit.

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: reading 'currently-killed' state before acting suggests an inspection-before-restore workflow, but the description never says when to call this versus fleet__restore_status, fleet__undo_status, or fleet__get_execution. No exclusions or prerequisites are given.

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