Diagnose application

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

Annotations already mark it read-only, so no safety ambiguity. The description adds value by disclosing that it includes the most recent failed deployment's log tail and suggested next actions, which is non-obvious behavior. It doesn't mention any edge cases (e.g., if no failed deployment exists), but the core behavior is clear.

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?

Two sentences, clear subject, no redundant phrasing. Lists contents in a structured way.

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 diagnostic aggregator, the description covers purpose, input, and output components. Without an output schema, it doesn't need to detail shape. The absence of any mention of error cases or response format is a minor gap, but the tool is well-specified for its scope.

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 descriptions cover both parameters fully (identifier format with UUID/name/domain, log_lines with min/max/default). The description repeats the identifier pattern but adds nothing beyond the schema. Baseline 3 applies due to high schema coverage.

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 uses the specific verb 'Diagnose' and enumerates concrete data points: current status, latest deployments, failed-deployment log tail, runtime logs, and suggested next actions. This clearly distinguishes it from siblings like getLogs or getApplication, which are single-purpose.

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 implies this is a one-call aggregate ('in one call'), but does not explicitly state when to prefer it over getLogs/getApplication or when not to use it. No alternatives are named. This is implied, not explicit.

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