papajohns_menu

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

With no annotations, the description carries full behavioral burden and mostly fulfills it. It explains the store_id default behavior, that the response is flagged with national_default, describes the response structure (categories, sections, product groups, SKU fields), and what include_options adds. It does not explicitly confirm read-only safety or discuss rate limits/auth, but for a menu-retrieval tool the stated behavior is substantial and non-misleading.

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 but every sentence earns its place: core action, pricing caveat, store_id sourcing, default behavior, response contents, include_options semantics, and geographic alternatives. It is somewhat long, but given the tool's complexity and the need to route among many sibling menu tools, the length is justified and front-loaded with the most critical facts.

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 tool with three parameters, no output schema, and no annotations, the description covers the key contextual gaps: input source, default vs. store-specific behavior, response composition, option expansion, and cross-country alternatives. It doesn't detail exact response serialization or error behavior, but it provides enough for an agent to select and invoke the tool correctly in most scenarios.

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?

Input schema coverage is 100%, so baseline is 3, and the description adds meaningful value on top: it explains why store_id matters (price variance between stores), where to obtain it, and the consequence of omitting it. It also elaborates on include_options, describing sizes, crusts, and preparation instructions in concrete terms. The category parameter is not enriched beyond the schema's enum, but the overall parameter semantics are well supplemented.

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 uses a specific verb and resource ('Get a Papa John's restaurant's priced menu') and clearly states scope: US or Canada restaurant's full menu with per-restaurant prices. It differentiates itself from sibling menu tools by explicitly naming geographic alternatives (India, intl markets), leaving no ambiguity about what this tool returns.

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 when-to-use guidance: pass a store_id from GET /papajohns/store or GET /papajohns/nearby to get store-specific prices, and warns that omitting it returns the national default menu. It also states clear exclusions, directing users to GET /papajohns/india/menu and GET /papajohns/intl/menu for other countries. This is exemplary routing guidance.

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