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

Annotations already declare readOnlyHint=true, and the description reinforces this with 'DATA ONLY, read-only'. It adds valuable context beyond the annotation by stating 'no HMAC required, no orders', explicitly ruling out authentication and trading actions. This transparency helps the agent understand the tool's safe, non-mutating nature without contradiction.

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 two concise sentences that front-load the core purpose and then list important safety constraints. Every word earns its place; there is no fluff or redundancy. The structure is clear and easy to parse.

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 11 parameters, 7 required, no output schema, and minimal annotations, the description must explain more about what the tool returns and how the gate works. It only lists input categories and safety guarantees, omitting the decision logic, output format, or how the 'composite' is computed. This is insufficient for a complex gate tool, leaving the agent with significant ambiguity.

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 0%, so the description must compensate for 11 parameters. It mentions conceptual inputs like 'CI lower bound', 'effect size', and 'slippage improvement', which roughly map to some parameters, but it does not define thresholds (metric_threshold), minimums (min_delta_sharpe, min_slippage_reduction_bps, min_sample_days), or settings like alpha and multiple_testing_mode. This leaves many parameters semantically unexplained.

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 is a 'Composite advisory gate over supplied statistics' and lists the key inputs (CI lower bound, effect size, slippage improvement, sample depth, Holm/BH p-values). This conveys the tool's purpose as an evaluative gate, distinguishing it from simple single-statistic gates. However, it does not explicitly state the output behavior (e.g., pass/fail or advisory score), so it stops short of full clarity.

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 no explicit guidance on when to use this tool versus sibling gates like apex_run_deflated_sharpe or apex_run_dynamic_penalty. It implies use when you have all the listed statistics, but there is no mention of alternatives, prerequisites, or when not to use it. This lack of usage context leaves the agent to infer appropriateness.

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