list_test_records

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

Annotations provide readOnlyHint=true. Description adds that return is summaries, id matches update_test_records record_id, and defect_id links failure work item. No contradictions.

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?

Five concise sentences, front-loaded with purpose, then guidelines, filter info, and output semantics. 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 output schema exists and 5 parameters, description covers main use case, result filtering, and key output fields. Pagination is implicit via schema defaults, but sufficient.

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 60%. Description adds meaning to result parameter (filter by enum ID, empty for not executed) and explains output fields. Other parameters well-covered by 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?

Description clearly states the tool lists execution records of one test run, one row per test case iteration, distinguishing it from get_test_run (metadata) and update_test_records (which uses the record_id).

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 directs to use get_test_run for run metadata, states Lucene query is not supported, and explains result filter behavior with empty result for not-yet-executed records.

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