Your Usual Groceries

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

Adds substantial behavioral nuance beyond annotations: refresh=true avoids double counting, counts are 'observed orders, not lifetime purchases,' 'quantities are unknown,' and cached URLs may be stale. These interpretation caveats are exactly the kind of context annotations cannot convey. No contradiction with annotations — the refresh semantics even help explain why readOnlyHint=false despite the 'Return' framing.

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?

Four sentences, each earning its place: core purpose, refresh semantics, interpretation caveats, and a routing pointer. The purpose is front-loaded, and sentences 3 and 4 pack two related facts each via semicolons without bloat.

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?

The output schema covers the return shape, and annotations cover safety and idempotency. The description covers the genuinely tricky semantics: double-counting on refresh, count interpretation, quantity limitation, cache freshness, and the need to verify price elsewhere. The only real gap is the implicit query parameter, a minor omission against an otherwise complete picture.

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 0%, so the description must compensate. It fully explains refresh=true ('incorporates the recent-order window without double counting'), but the query parameter is never named or described — its role as a product lookup term is only implied by the tool's overall purpose. One of two parameters is left to inference.

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?

States a specific verb and resource: 'Return account-scoped product frequency, observed orders, and remembered choices.' This clearly distinguishes it from siblings: get_product handles current price/promotions, search_products handles discovery, and remember_product/forget_shopping_memory handle memory writes and deletes. The title 'Your Usual Groceries' reinforces the recall role.

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?

Explicitly routes to an alternative with a condition: 'verify current price and promotions with get_product,' and explains when to set refresh=true ('incorporates the recent-order window'). However, it never explicitly distinguishes itself from the closely related memory siblings remember_product and forget_shopping_memory, leaving part of the routing to inference.

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