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

Annotations only declare readOnlyHint=true, but the description adds substantial behavior: it reads the demo record, the staging namespace state (deployment ready/desired, pod waiting/terminated reasons with restarts, service endpoints, ingress/TLS, cert-manager readiness, newest Warning events), and performs a live URL probe from the Ankra platform with failure_stage classification. It also discloses the read_failures semantics ('an empty inventory list means absent only when read_failures is empty'), which is exactly the kind of caveat 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 trigger condition and the action, and every sentence carries information (what it reads, what it returns, what to avoid, how to identify the demo). The middle paragraph is a single very long sentence enumerating collected fields, which is dense but not wasteful; minor readability cost.

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?

No output schema exists, and the description compensates fully: it describes the verdict format ('first broken hop in plain words' with an example), the probe fields, the failure_stage values, and the read_failures caveat. An agent has everything needed to call and interpret this tool without further discovery.

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 100%, so the baseline is 3, but the description adds a real disambiguation rule: identify the demo by workspace_id, namespace or preview_url — any one — and points to list_application_demos for obtaining all three. It also states application_id is the required anchor for the Application. That is meaningful added semantics beyond the property descriptions.

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?

Starts with a precise verb+resource+trigger: 'The first call for any question about an Application demo or preview that does not work, does not load, times out...'. It clearly distinguishes itself from neighbors like get_demo_diagnostics, redeploy_demo and list_application_demos by enumerating the failure symptoms it owns.

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?

Explicitly says it is the first call for demo/preview failures, names list_application_demos as the source of identifiers, routes crash-looping containers to get_demo_diagnostics for the log tail, and instructs the agent NOT to re-read pods, services, ingresses or events itself.

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