Application health

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

With no annotations provided, the description carries the full burden and excels: it declares read-only, deterministic behavior, no mutation/shell/SSH/network/secrets, precisely defines the UNAVAILABLE vs UNKNOWN semantics, and clarifies that evidenceAgeSeconds is factual and never alters the status. The negative list of non-behaviors is unusually thorough.

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?

The description is dense but every sentence earns its place: verdict values, source identity, status semantics, exclusions, and safety guarantees. It is front-loaded with the core purpose. It runs long relative to its simple scope, but given there are no annotations or parameter descriptions to lean on, the length is justified.

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 zero-parameter, deterministic read tool with an output schema present, the description is complete: it covers the verdict space, source provenance, status meaning, evidence-age semantics, exclusions, input contract, and safety profile. Nothing an agent needs to invoke it correctly is missing.

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?

With zero parameters, the baseline is 4, and the description adds meaningful reinforcement beyond the empty schema by stating 'Input must be exactly {}' and explaining why ('no new configuration'), which helps an agent understand there is genuinely nothing to supply.

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 states a specific verb+resource (reports application health state from the configured evidence source) and enumerates the exact verdict domain (HEALTHY | DEGRADED | UNKNOWN | UNAVAILABLE). It explicitly distinguishes itself from siblings by declaring what it does NOT do: probe the application, inspect Docker, call HTTP, infer from deployment status, or diagnose root cause.

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 clear context positioning it as sharing 'the same source and configuration as engineering.deploy.status' and provides explicit when-not boundaries (not for probing, Docker inspection, HTTP calls, root-cause diagnosis). It falls just short of a 5 because it doesn't explicitly name the alternative tool to use for each excluded case.

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