mcdonalds_item_list

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It explains the return content: 'Returns the same published nutrition detail as GET /mcdonalds/item for up to 20 items in one call, plus the per-component ingredient and allergen breakdown.' It also discloses the response echoing behavior: 'The response echoes the requested ids so a caller can tell which ones McDonald's returned nothing for.' This is transparent about what the caller receives, though it doesn't mention rate limits or auth, which are not critical for a read operation.

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 moderately long (around 150 words) but well-structured. It front-loads the primary purpose, then explains the distinguishing feature (per-component breakdown), and finally provides operational details. Every sentence adds value; there is no fluff. It could be slightly more concise, but the length is justified by the need to explain the nuance of composite item allergens.

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's complexity (batch, per-component breakdown, market-specific ids, echoing behavior), the description covers all key aspects a caller needs: what it returns, how it differs from the single-item endpoint, where ids come from, and how to handle missing items. Without an output schema, it doesn't detail the exact response structure but provides enough context for the agent to use it correctly. There is no mention of error handling or rate limits, but these are not critical for this read operation.

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 the schema already documents both parameters. The description adds some context: 'Item ids come from GET /mcdonalds/menu and are market-specific, so pass the same country back.' This slightly reinforces the schema's instructions but doesn't add significant new information beyond what the schema already says (e.g., country must match the market). The description does not introduce new parameter nuances, so a baseline score of 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 purpose: 'Get nutrition and allergen detail for a batch of McDonald's items.' It specifies the resource (McDonald's items) and the action (get). It also distinguishes from the sibling tool by explicitly contrasting with the single-item endpoint: 'plus the per-component ingredient and allergen breakdown that the single-item endpoint does not expose.' This makes the purpose unambiguous and differentiates it from mcdonalds_item.

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 this tool: 'so this is the source to use when the full breakdown matters, not just the item-level summary.' It also provides operational context: 'Item ids come from GET /mcdonalds/menu and are market-specific, so pass the same country back.' This tells the agent how to source parameters and implies the alternative (use single-item when only summary needed).

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