SmartProspect: list cities

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

The description goes well beyond the annotations by explicitly enumerating safety properties: read-only, no credit consumption, no remote state changes, no email, not destructive. It also discloses that it does not reveal contacts and includes a specific behavioral note about the country/state filter requirement. This is excellent context beyond the structured 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 reasonably concise and front-loaded with the core purpose. Every sentence adds value (purpose, safety, endpoint, reference data, dependency note), though the safety line and reference data sentence slightly overlap on the 'no credits' point, making it a touch redundant.

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?

Given the tool is a simple reference-data listing with an output schema available, the description provides all needed context: purpose, endpoint, safety profile, and a known filter constraint. The output schema covers return values, so the absence of further return details is not a gap.

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 baseline is 3; each parameter already has a clear description. The description adds no new parameter details, only repeating the country requires state note already present in the schema. This does not elevate above baseline.

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 exactly what the tool does: 'List city values available as SmartProspect search filters.' This is a specific verb + resource, and the 'cities' focus clearly distinguishes it from sibling list tools (states, countries, departments, etc.). The endpoint is also provided for additional clarity.

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 provides context by noting this is 'Reference data only' and 'Does not reveal contacts and does not consume credits,' implying it should be used for filter dropdowns rather than contact discovery. It also mentions the country/state dependency. However, it doesn't explicitly contrast with sibling alternatives (e.g., 'use list_states for states') or state when not to use it.

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