sonic_menu

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

No annotations are provided, so the description carries the full burden. It goes beyond a simple mutation/read statement: it discloses the data source (only calories, no price/full nutrition), explains that some entries are nested size/variant groups rather than single orderable products, and clarifies what the source does not contain. This is genuinely useful behavioral context. It doesn't discuss pagination, limits, or stability, but for a simple list tool this is adequate. The nested variant group caveat is a valuable behavioral disclosure that an agent would not otherwise know.

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 focused paragraph that front-loads the main action and then adds critical caveats about the return content and sourcing. It could arguably be split into clearer sentences or bullet points for garnish, but every sentence adds substantive value and there is no redundancy. It is not overlong; it is adequately dense for the caveats it needs to convey.

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 list tool with no output schema, the description covers what the tool does, what the input is, where the input comes from, what the output contains, and the known limitation (no price/full nutrition, only calories; some entries are variant groups). For an agent, this is nearly complete. A minor gap is the absence of return structure or pagination, but the description is quite poor for a nutrition/data-quality context and this tool is quite poor. It is close to complete for its purpose.

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% per context signals, so baseline should be around 3. But the description adds meaningful beyond-schema meaning: it explains the category parameter is a slug, states where the slugs come from (GET /sonic/categories), and gives an example of what a category can contain (Coffee expands to sizes). This exceeds the baseline by clarifying the semantics of the parameter and its provenance.

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 opens with a specific verb and resource: 'List one Sonic Drive-In menu category's items'. It then adds scope details (returns items with name and published calorie count) and importantly differentiates itself from sibling tools by stating category slugs come from GET /sonic/categories, and points to GET /sonic/item for richer data. An agent can clearly distinguish this from sonic_categories, sonic_item, and menu-related siblings without opening schemas.

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 provides clear context for when to use this tool: when you need a category's items and calorie counts. It also says where category slugs come from, and mentions GET /sonic/item for description/image/nutrition link. However, it does not explicitly state when not to use it or name the alternative tool for detailed info, though it essentially does by pointing to /sonic/item. It lacks an explicit 'use sonic_item instead for details' statement but the guidance is implied clearly.

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