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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint, so the bar is lower. The description adds valuable behavioral context by explaining that the tool includes provisions inherited from parent categories and why ('since a GSFA provision applies to a category and all of its subcategories'). This goes beyond annotations by disclosing a specific expansion behavior. It does not contradict annotations.

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 three sentences with no wasted words. It front-loads the main purpose, then explains the inheritance rule and provides a use case. Every sentence earns its place, making it easy to scan and understand quickly.

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 simple listing tool with all parameters documented in the schema, the description covers the essential context: what it lists, that it includes inherited provisions, and when to use it. It also hints at the output format ('with each maximum use level'). With no output schema, this is sufficient for an agent to decide when to call it, though it could benefit from mentioning that results may be large or that it complements other GSFA tools.

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 coverage is 100%, so all parameters (food_category, limit, include_inherited) are already documented. The description adds minimal parameter-specific meaning; it mentions 'given Codex GSFA food category' which maps to food_category, and the inheritance behavior indirectly relates to include_inherited, but it does not add syntax or format details beyond the schema. Baseline 3 is appropriate.

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 function: 'List every food additive permitted in a given Codex GSFA food category, with each maximum use level.' It specifies the resource (Codex GSFA food category) and the action (list additives), and it distinguishes itself from sibling tools like gsfa_search_additive by focusing on category-based listing rather than additive-based search.

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 explicit guidance on when to use the tool: 'Use to see what additives may legally be used in a particular food.' It also clarifies that inherited provisions are included, which is useful context. However, it does not explicitly name alternative tools or state when not to use it, though the use case is clear enough to differentiate from siblings.

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