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

Beyond the annotations it discloses the auth scope required, the RED escalation criteria (stale, failed, local-only or never-drilled backup), that the request is asynchronous with a 15-minute pickup window, that queuing is audit-logged, and that target credentials are never returned ('host/bucket, never keys'). The mutation available via start is consistent with readOnlyHint=false and destructiveHint=false.

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?

Content is front-loaded: the access precondition and the core question come first, the RED rule next, the write path after, and the return shape last. It is dense and the opening sentence is a long comma-and-colon chain, but nearly every clause carries information an agent needs; nothing is padding.

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 description compensates by naming the returned keys ({health, reasons, targets, problems, schedule, runs, started?}), and it explains the health semantics, the async caveat, and the credential-hygiene guarantee. An agent can call this correctly and interpret the result without further documentation.

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 the baseline is 3; the description earns an extra point because it gives the two valid values ('backup' or 'drill') and, more importantly, their effect and latency: the job is queued for a worker, picked up within 15 minutes, and audit-logged. That is behavioral meaning the schema does not carry.

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?

The description opens with a concrete verb and resource ('Backup and restore-drill health') and then enumerates the exact facts it reports: newest backup verified on an offsite target and its age, Object Lock immutability, last passing restore drill, worker liveness, targets, schedule and recent runs. That is far more specific than the tool name and lets an agent distinguish it from health-adjacent siblings such as merjax_ci_health or merjax_repo_health.

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 states the access precondition clearly ('Site admins only (needs an admin-scoped token)') and explains both modes: read-only inspection by default, and passing start: 'backup' or 'drill' to queue work. It does not name an alternative tool or a when-not-to-use condition, but the resource is narrow enough that no close sibling competes.

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