diagnose_test_failure

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

With no annotations provided, the description must disclose behavioral traits. It only lists high-level outputs but does not mention side effects (e.g., if it modifies any state), required permissions, rate limits, or what happens with invalid inputs. The description lacks transparency about the tool's behavior beyond its result.

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 a single sentence that efficiently conveys the core functionality. However, it is in Portuguese while the tool name is English, which may reduce clarity for some agents. Otherwise, it is concisely structured with no wasted words.

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?

Given no output schema and no annotations, the description should provide more context about the return format, whether the fix is a suggestion or code, and how the inputs are used. It leaves important details for the agent to infer, making it incomplete.

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?

The input schema has 100% description coverage, so each parameter's purpose is already clear. The description adds 'root cause, type, fix' but doesn't directly map to parameters, providing marginal additional value. Baseline 3 is appropriate given 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 clearly states the tool's purpose: 'Diagnoses failure in existing test: identifies root cause, classifies type (flaky, regression, environment) and suggests fix.' It specifies the resource (test failure), the action (diagnose), and the outputs (root cause, type, fix), making it distinct from sibling tools like 'analyze' or 'generate_test_suite'.

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 provides no guidance on when to use this tool versus alternatives, such as the async sibling 'task_diagnose_failure_async'. It does not mention prerequisites, typical scenarios, or exclusions, leaving the agent without context for selection.

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