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

Beyond readOnlyHint, it discloses that this is a plain database read of the bastion_health loop's last observation, that it 'answers immediately and never touches the host', and that an empty state/checked_at means unprobed. The provider-lane caveat (Scaleway Public Gateway has no diagnosis lane) is behavioral context the annotations cannot carry.

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?

Front-loaded with the purpose and the routing rule, with no filler sentences. It is denser and longer than strictly necessary, but each clause carries distinct information (return fields, read semantics, caveats, exclusions).

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?

There is no output schema, so the description compensates by enumerating the returned fields (state, failing hop, failure detail, consecutive failures, provider view, last probe time). Combined with the empty-state semantics and the no-bastion cluster types, an agent has everything needed to call and interpret it.

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% and the single cluster_id param is fully described in the schema itself, including how to discover ids via list_clusters. The description adds no parameter-level syntax or constraints, so the baseline 3 applies.

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 ('Report the SSH bastion health verdict... for an Ankra-provisioned cluster') and enumerates exactly what the verdict contains. It explicitly separates itself from the sibling diagnose_bastion, so an agent can route 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?

Gives explicit when-to-use ('use it, not diagnose_bastion, to answer "is the bastion up?"'), when-not ('Reach for diagnose_bastion only when the host itself must be inspected over SSH'), and a gating condition ('only when this tool reports diagnose_supported true'). It also names exclusions: agent-reached imported/managed-K8s clusters have no bastion.

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