Detailed crime data for one ZIP code. Use when get_zip_profile's crime section isn't sufficient depth. Includes violent crime rate, property crime rate, and data quality flags (coverage level, Bayesian shrinkage).
| Name | Required | Description | Default |
|---|---|---|---|
| zip | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must convey behavioral traits. It lists the returned data fields, which implies a read-only operation, but does not explicitly state safety (no side effects), error handling (e.g., invalid ZIP), or performance considerations. The description provides some transparency but lacks details that would fully inform the agent about expectations.
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, front-loading the purpose and use case. Every sentence provides value: the first states the action and scope, the second adds depth and differentiation. No unnecessary words.
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's simplicity (one parameter, no output schema) and the presence of many sibling tools, the description covers the essential context: what it does, when to use it, and what it returns. It lacks error behavior or rate limits, but for a data retrieval tool, the coverage is adequate.
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 0%, so the description must supplement. It clarifies that the tool accepts 'one ZIP code,' implying a single string identifier. However, it does not specify the expected format (e.g., 5-digit, numeric string) or provide constraints beyond the schema's title 'Zip.' This adds some meaning but not comprehensive guidance.
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 it provides detailed crime data for one ZIP code, with specific components (violent crime rate, property crime rate, data quality flags). It explicitly distinguishes from the sibling 'get_zip_profile' by indicating when to use this tool (when the crime section of the sibling is insufficient). This is a specific verb+resource with clear differentiation.
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 gives explicit guidance: 'Use when get_zip_profile's crime section isn't sufficient depth.' This tells the agent when to select this tool over the sibling. While it doesn't list other alternatives or negative cases, the guidance is direct and actionable.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Every tool has a clearly distinct purpose. Domain-specific profiles (e.g., get_air_quality_profile) are explicitly for deeper dives after get_zip_profile, while search, reverse geocode, research, and methodology tools each serve unique roles with no overlap.
All tools follow a consistent verb_noun pattern: get_<domain>_profile, search_zips, reverse_geocode, compare_zips, get_research, get_methodology, etc. The naming is predictable and clear, with no mixing of conventions.
22 tools is slightly above the typical well-scoped range, but each tool addresses a specific need (12 domain profiles, search, geocoding, articles, methodology, ping). The count is appropriate for the breadth of data offered.
The tool surface covers the full workflow: discover (search_zips, get_search_fields), retrieve (get_zip_profile, domain profiles), compare (compare_zips), and ancillary (reverse_geocode, get_research, get_methodology). There are no dead ends or obvious gaps.
