ht_get_receipt

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the baseline safety profile is covered. The description adds genuinely non-obvious behavioral context: the upstream site intermittently rejects the request due to bot protection, and there is a manual fallback path. It stops short of describing retry behavior, failure signal shape, or whether an error is distinguishable from an empty result.

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?

Three sentences, each load-bearing: what you get, what you must supply, and what to do when it breaks. The payload contents are front-loaded so an agent can decide relevance before reading the operational caveats.

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 two-parameter read tool with no output schema, the description substitutes well by enumerating the returned fields, stating the required input's source, and covering the one known failure mode with a fallback. Nothing an agent needs to call this correctly or interpret a failure is absent.

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 50%: the `view` enum is thoroughly documented in the schema, but `receiptKey` has only length bounds and no semantic description. The sentence "Pass a receiptKey from ht_list_orders" compensates for exactly that gap by naming the key's provenance, which is the one thing the schema omits. The `view` modes are left entirely to the schema, which is acceptable given how detailed it is.

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?

"Read one Harris Teeter purchase in full" names a specific verb and resource, and the enumeration of contents (items with quantity, price paid, savings, subtotal, coupons, tax, total) makes the scope unmistakable. This is clearly distinct from the sibling ht_list_orders, which surfaces the keys rather than the detail.

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?

"Pass a receiptKey from ht_list_orders" establishes the prerequisite and points to the exact sibling that supplies it, and the bot-protection fallback (use My Purchases on harristeeter.com) gives an explicit alternative when the tool fails. What's missing is any statement of when an agent should prefer the list tool instead of drilling into a single receipt, so it falls just short of fully explicit routing.

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