test_fix_web

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

No annotations are provided, so the description carries full burden for behavioral disclosure. 'Fix failures' is ambiguous — it's unclear whether the tool autonomously modifies code, requires approval, or only suggests fixes. For a tool that both tests AND fixes (a potentially mutating action), there's no disclosure about what gets modified, whether changes are automatically applied, or any failure handling behavior. This is a significant gap for a tool with destructive implications.

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, efficient sentence with no wasted words. It conveys the core purpose compactly. However, it's slightly under-specified given the mutating 'fix' action, but brevity isn't the issue — completeness is.

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 tool that performs both testing and code-fixing (a mutating operation), the description is too thin. There's no output schema, no annotations, and no explanation of what 'fix failures' entails (scope of fixes, safety, reversibility). Given the number of sibling test/fix tools, more context about which scenarios warrant this specific tool would be valuable. The description is adequate as a label but incomplete as operational guidance.

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 single 'spec' parameter is fully documented in the schema with its enum values and description. The description adds the domain context (that the spec relates to machine specifications, implicitly). Baseline 3 is appropriate since the schema handles parameter documentation and the description adds marginal connection to the Next.js context.

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 clear verb ('Run tests') and resource ('Next.js application') with an explicit action ('fix failures'). It identifies the tool as a combined test-and-fix workflow. Distinguishes itself from siblings like test_fix (non-web variant) and test_fix_incremental via the 'Next.js application' scoping and failure-fixing focus.

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?

No guidance on when to use this tool versus alternatives like test_fix, test_fix_incremental, or test_fix_incremental_web. The sibling set has several test/fix variants, and the description provides no criteria for choosing among them (e.g., when incremental is preferred, when to use non-web variants). Users must guess whether 'fix failures' means auto-fixing or only reporting.

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