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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds substantial behavioral context beyond annotations: the exact JSONL block structure ('>>>>> RuleKey:' headers, a JSON Schema line with tooltips and column types, main rows with detail rows nested under 'children'), and the notable behavior that rules with no completed run in the last 30 days contribute no block.

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 dense and well-structured: verb+resource first, then output format, then use case, then the 30-day caveat. Every clause adds unique information—block structure, schema line contents, children nesting, raw-findings purpose, and the no-block condition—with no repetition or filler.

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?

With no output schema present, the description correctly carries the return-format burden and does so thoroughly (block structure, nesting, per-rule behavior). Minor gaps remain: block ordering across multiple rules, error behavior for invalid rule keys or account IDs, and row ordering are unspecified. For a 4-parameter tool with 100% schema coverage, this is near-complete.

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 baseline is 3. The description loosely maps to parameters ('one account' → accountId, 'one or more rules' → ruleKeys) but adds no parameter-level detail beyond what the schema already provides. The schema itself carries the semantic load here.

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 specific verb+resource+scope: 'Get the detailed output rows for the latest completed audit run of one or more rules for one account.' The qualifier 'latest completed' and the 30-day window clearly distinguish this from the sibling audit_rule_output_table_historical, and the output format (multi-block JSONL) is specified in the first sentence.

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 gives clear usage context: it provides 'the raw findings behind a failing audit rule' and applies to the 'latest completed audit run' with a 30-day window. However, it does not explicitly name alternatives (e.g., audit_rule_output_table_historical for older runs) or state when-not-to-use conditions, so it stops short of the explicit routing a 5 would require.

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