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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is lower, yet the description adds real value: it is a live validation that depends on current stock and fitting capacity and touches nothing (no order, reservation, email or charge). It stops short of stating failure modes (e.g. what happens when stock or a fitting slot is unavailable) or whether the quoted price has a validity window.

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 short sentences, front-loaded with the outcome the agent cares about, with the disambiguating negation at the end. Every clause earns its place.

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 5-param tool with nested items/fitting objects and no output schema, the description conveys enough to call it correctly: what is priced, that stock and capacity are validated, and that nothing is committed. The shape of the returned quote is only hinted at ('line by line'), and error behavior is unspecified.

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% and each parameter carries rich text, including cross-references to search_tyres, list_fitting_days and get_shop_info. The description adds little param-level meaning beyond 'these tyres and options', so the baseline 3 applies.

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 output ('the exact total ... line by line, exactly what the payment page will charge') plus the validation performed ('checks stock and fitting capacity'). The closing negation ('does not order, reserve, email or charge anything') cleanly separates it from place_order, so an agent can distinguish it from siblings without opening schemas.

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 explicit list of things it will not do defines the non-committal path and strongly implies it precedes place_order, and the stock/capacity check tells the agent why to call it. It never names place_order as the alternative to reach for when the user actually wants to buy, so the routing is implied rather than stated.

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