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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is covered. The description still contributes real behavioral information: results are 'retained' (a stored snapshot, not recomputed) and the response reports currentness, telling the agent the data may be stale. Only the undefined nature of 'candidate currentness' keeps this from a 5.

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?

One sentence, front-loaded with the action and resource, ending with the key constraint ('no model rerun'). No filler or redundancy.

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 two-parameter read tool with a full schema, complete parameter descriptions, annotations, and an output schema, the description covers what is needed to invoke it correctly. The one gap is that the currentness semantics returned are not clarified, which matters for interpreting results but not for calling the tool.

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%, with both agent_id and result_id documented in the schema including their source tools. The description adds only the notion that result_id refers to a retained result, which the schema already conveys, so baseline 3 applies.

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 names a specific verb and resource ('Returns one retained preview result') and adds the secondary payload ('its candidate currentness'), which separates it from siblings like test_case_run or test_case_evaluate. It loses a point only because 'candidate currentness' is unexplained jargon an agent may not decode.

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 model rerun' implicitly signals this is the cheap read path versus actually evaluating a test case, which is useful context. However, it never explicitly states when to prefer this over test_case_read, test_case_run, or agent_setup_read, and gives no prerequisites or exclusion conditions.

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