test_recommendation

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

With no annotations, the description carries full burden. It reveals the scoring formula (risk weights × confidence), thresholds, and categorization. It does not explicitly state read-only behavior, but the recommendation nature implies no destructive actions. The behavioral context is well disclosed.

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 concise with no wasted words. It uses an effective structure: main purpose, usage examples, and formula in separate blocks. Every sentence adds information.

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?

The description assumes knowledge of 'Phase 2' without explanation. It describes output as categories and a minimal test set, but does not specify exact output structure (e.g., list of test cases with scores). Given no output schema, more detail on return format is needed.

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 coverage is 100%, baseline 3. The description adds value by giving concrete examples (e.g., name='gh-backend' for repo alias, module='用户中心' for module analysis) and explaining defaults for from/to (current watermark, remote HEAD). This enriches the schema.

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 it recommends test execution order based on code changes and Phase 2 impact analysis, generating a minimal viable test set. The examples further clarify usage with name and module, distinguishing it from sibling tools like impact_analysis and risk_assessment.

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 explicit usage examples (name vs module) and explains the scoring formula and threshold categories. It implies that Phase 2 analysis should be done first, but does not explicitly state when not to use this tool or directly compare with all siblings.

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