Score a draft against the For You rules (free, no API call)

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds valuable context beyond these: it enumerates the exact rules evaluated (URL weights, spam triggers, engagement-bait patterns) and confirms there are no side effects. It also mentions 'concrete suggestions,' though it does not elaborate on output format. Since annotations carry the safety profile, the description earns credit for enriching the behavior picture.

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 a single dense sentence packed with specific metrics and rules, each earning its place. It is front-loaded with the core action ('Run the algorithm rules engine on a draft') and immediately provides actionable details. While dense, there is no fluff; even 'Costs nothing' is a useful differentiator. The length is appropriate for the technical specificity.

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?

Given the tool has 4 parameters, no output schema, and moderate complexity, the description explains the scoring logic thoroughly but omits return value format (score, warnings, suggestions shape). It also does not clarify how 'kind' affects scoring despite listing reply/quote weights. Annotations help, but with no output schema, the description should describe what the agent receives, which is missing. Still, it provides enough workflow context (score ≥80) to be partially 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 50% (limit and variants have descriptions). The main description adds some context by implying that 'draft' refers to the text parameter and mentions weighted length and mention counts tied to text content. However, it does not explain the 'kind' enum's impact on scoring (though it hints 'reply 5→20') or the purpose of 'variants' beyond an implicit side-by-side comparison. It partially compensates but does not fully bridge the gap for undocumented parameters.

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 the tool's purpose: 'Run the algorithm rules engine on a draft' and lists specific checks (weighted length, mentions, URL cost, engagement-bait, hashtags, ranking heads). It also provides a concrete workflow ('Iterate until score ≥ 80'), distinguishing it from sibling tools like publish or reply, which are actions rather than assessments.

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 implies usage by instructing 'Iterate until score ≥ 80 with no warnings, then publish,' establishing a clear pre-publish check workflow. It also notes 'Costs nothing,' which differentiates it from potential paid alternatives. However, it does not explicitly name alternative tools or state when not to use it, so it misses explicit exclusions.

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