analyze_test_results

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

With no annotations, the description fully discloses behavioral traits: no LLM in call path, deterministic results, how flaky thresholds work, handling of malformed/oversized input returning an error struct, and the never_run logic for reference_tests. Provides clear expectations for the agent.

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 lengthy but every sentence adds value. It front-loads the core purpose and constraints, then details input formats and behaviors. Slightly verbose but justified by complexity; 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 the tool's complexity (multiple input formats, flakiness analysis, reference tests) and no output schema, the description provides complete coverage: input formats, output structure (ResultsAnalysis JSON), error handling, and edge cases like insufficient data for flaky detection. Fully equips an agent to use the tool correctly.

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 0% description coverage, but the description compensates thoroughly: explains junit_xml format (string vs JSON array), csv_text columns (name/classname/status/optional fields), flaky_min/max defaults, and reference_tests format ('classname::name'). Adds meaning far beyond the bare 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 provides 'Deterministic test-results health metrics' with a specific list of outputs (flaky, ever-failing, never-run, slowest, failure clustering). It immediately distinguishes itself from unrelated sibling tools (retrieve_qa_knowledge, etc.) by focusing on test execution data analysis.

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?

Explicitly instructs to provide exactly one of junit_xml or csv_text, explains how to handle multiple runs via JSON array, and describes the optional reference_tests parameter. While it doesn't explicitly state when not to use this tool, the sibling tools are in a different domain, so the usage context is clear.

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