get_delivery_timeslots

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 discloses the requirement of an authenticated session, and implies this is a read-only operation (retrieves) with no side effects. It adds context about the return values (days, availability cells, collaborative delivery type). However, it doesn't specify behaviors like whether it uses cached data, rate limits, or what happens when no slots are available. It also doesn't mention whether it refreshes the session or mutates state, but the parenthetical about authentication is a positive.

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 two sentences long and packs in the purpose, return value, use case, and authentication requirement. No wasted words. It loses one point because the structure of 'Retrieves X. Returns Y. Useful for Z. (requires authentication)' is somewhat choppy but still highly efficient.

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 1 param, no output schema, and no annotations, the description is quite complete. It tells the agent what it does, what it returns, when it's useful, and the auth prerequisite. It could add more about failure modes or response structure, but compared to typical sibling tools ity knows a lot. The absence of output schema puts some burden on the description to describe the return, which it does at a high level.

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% and the parameter is well-documented in the schema itself, including an example format ('0678-150-149'). The description adds the concept of 'facility/store service' but mostly relies on the schema. Since there's only one parameter and it's thoroughly explained in the schema, the description earns a high score, though it doesn't explicitly repeat or recontextualize the parameters, but with such good schema, that's acceptable per the rubric.

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 clearly states the tool 'Retrieves available delivery or drive time slots for a specific facility/store service' with specific verb and resource. It adds context about the Carrefour France scope and the return value (list of days with time slot cells). While it doesn't explicitly name a sibling to distinguish from, the description implies it's for browsing slots, and the sibling 'select_cart_delivery_slot' suggests a different action (selecting vs retrieving). Clear but could have been more explicit about the difference from similar tools like 'validate_checkout_slot'.

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 implies usage ('Useful for letting the user pick a delivery or click-and-collect time window') and mentions a prerequisite ('requires an authenticated Carrefour session'). It also notes the need for a facilityServiceId. However, it doesn't explicitly say when NOT to use this tool or contrast it with alternatives like 'validate_checkout_slot' or 'select_cart_delivery_slot'—though the sibling names are suggestive, the description takes no credit for that.

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