Get Cities

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

Annotations already mark it read-only, non-destructive, and closed-world, and the description adds important behavior beyond that: catalog presence is not availability/order coverage, a coordinator confirms after buyer submission, nickname/borough resolution works, unfiltered results are capped, and there are 345 configured entries. No contradiction with annotations.

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 front-loaded with the core capability and key caveat, then lays out intents, alternatives, examples, and hints in a scannable structure. Each section adds distinct value, and the angle-bracketed examples and hints keep the prose tight.

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-parameter, 0-required-parameter read-only tool, the description covers what triggers it, how to invoke it for the key 'Do you cover...' case, input-form nuances, cap behavior, and the necessary caveat about confirmation. With an output schema present, return details need not be spelled out; nothing critical is missing.

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 parameter semantics are already documented well. The description adds useful extra guidance through concrete examples and hints: state accepts full names, country accepts 'US'/'CA', city resolves nicknames/boroughs, and limit affects returned rows while counts remain in totals. This is meaningful but not essential enrichment.

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 states a specific action ('List' / 'match') and a specific resource ('configured market entries'), and further clarifies that catalog presence is distinct from availability/order coverage. It names sibling tools it is NOT (check_availability, get_role_pricing, plan_staffing), so an agent can differentiate it from the rest of the toolset.

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 maps natural-language intents to this tool ('What markets are configured in [state]?', 'Is [city] in the catalog?', 'Do you cover [city]?') and provides the exact invocation pattern with city. It also states when to use sibling tools instead: get_role_pricing for rates, check_availability for dates, plan_staffing for a full plan.

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