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

The description goes well beyond the readOnly/destructive annotations by explaining the ranking methodology: information-per-friction, entropy from the discrimination matrix, governance outweighing effort, and equal weighting of live stories absent priors. It also discloses that the output includes both immediate and legal-review-needed asks, which is useful behavioral context beyond what annotations provide.

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 mostly front-loaded, opening with the core question before explaining ranking details. It repeats the title almost verbatim, which is mildly redundant, but every major sentence adds useful information about outputs, assumptions, or invocation. It earns a strong score despite being slightly verbose.

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 complex planning tool, the description is remarkably complete: it states the outputs, the ranking formula, the fairness assumption, the legal-review split, and the query parameter syntax. Since an output schema exists, the description does not need to explain return value structure. An agent has enough information to understand what the tool does and when to call it.

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?

The input schema is a generic body object with no property-level detail, so the description must carry the parameter-semantics burden. It does so by naming the GET query parameters (?live=, ?have=, ?lack=) and specifying comma-list format. However, it does not explain the semantic meaning of each parameter, such as precisely what live, have, and lack represent, leaving some inference to the agent.

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 purpose: given candidate data-stories, return the single most efficient next question, a full ranked list, and the minimum set of asks needed to make every live story testable. This clearly distinguishes the tool from the sibling get_* tools because it is a planner/optimizer, not a simple fetcher.

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: use when you have candidate data-stories and need to decide what data to ask for next, including a split of what can be sent today versus what needs legal review. It also references the query parameters live, have, and lack, which signals how to invoke it. It does not explicitly name alternative tools or say when not to use it, but the context is strong enough for an agent to select it appropriately.

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