plan_shopping

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

With no annotations, the description carries the full burden. It discloses the return shape (primary plan plus alternatives), that items can be generic or SKU-pinned, and how each strategy trades off stops versus cost. It doesn't state that no purchase is made or how expensive the search is, but for a read-only planner the disclosure is solid.

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 purpose and triggering scenarios are front-loaded, followed by the strategy distinctions, with no filler. Every sentence adds either selection guidance or behavioral context.

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 six-parameter planner with no output schema, the description says a primary plan and alternatives are returned but not what those contain (prices, per-store breakdowns, cost estimates). The parameter side is covered by the rich schema, but the return-value side is thin for a tool of this complexity.

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 100%, so the schema already documents every parameter in depth. The description adds little beyond what is in the schema – it restates that items may be generic or pinned and repeats the strategy meanings already given in the enum description. Baseline 3 is correct.

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 gives a specific verb and resource – "Plan a multi-store shopping trip near a location, picking the best products across configured Swiss grocery chains" – which is clearly distinct from sibling tools like search_products or find_stores. An agent can tell this is the multi-store optimizer, not a single-product search or store lookup.

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?

It explicitly states the triggering scenario (a list of items plus "where should I shop?" or "what's cheapest?") and explains the three strategies. It does not explicitly name which sibling to use instead for a single product lookup, but the context is clear enough to route correctly.

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