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

Annotations already advertise a safe, idempotent read, so the description invests in what annotations cannot say: the output is a normalized/cleaned rule with warnings, failures return a diagnosis, and the optional confirm block routes each buy through Jev using the runner's own key while backtests skip it. That key-ownership and backtest-exclusion detail is genuinely additive; return shape is described only loosely.

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?

Three sentences, front-loaded with purpose and return contract before usage and the optional Jev feature. Dense but each sentence carries information; the parenthetical Jev example is the longest stretch and edges toward schema duplication.

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 single-parameter tool wrapping a deeply nested rule object with no output schema, the description covers what comes back (cleaned rule, plain-language rendering, warnings, or the specific error), when to call it, and the one non-obvious optional behaviour. Nothing an agent needs before invoking it is missing.

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% and every nested field (when/until kinds, venue, leverage, confirm) is already documented inline, so the schema carries the load. The description restates the confirm option with a concrete example and adds that it runs under the person's own Jev key, but supplies no extra syntax guidance beyond the 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?

States a specific verb and resource ('Validates a rule in Dolphin's rule language') plus the exact return contract: the rule cleaned into plain words, warnings such as leverage, or precisely what is wrong. That is enough for an agent to distinguish it from backtest_rule and test_strategy without opening any schema.

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 names the sequencing ('Use before backtest_rule') and a second use case (helping someone author a rule for their agent). It gives clear positive guidance and points at the sibling that follows, but never states when not to reach for it, e.g. that it does not run a live rule or fetch market data.

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