The core tool: what the EPA has on record for a city's tap water — the active community water systems serving it, populations, sources, and violations (contaminant, health-based or not, dates, status, level vs limit when recorded). Plain-English, sourced, never a safety verdict.
| Name | Required | Description | Default |
|---|---|---|---|
| city | Yes | ||
| state | Yes | 2-letter state code, e.g. 'VT'. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, destructiveHint, and idempotentHint. The description adds that the data is 'Plain-English, sourced, never a safety verdict,' which clarifies behavioral traits beyond the 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 two sentences, tightly packed with essential information, and front-loaded with the core purpose. No wasted 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 complexity of retrieving water data and the presence of annotations, the description adequately covers the return content and behavioral nuance (no safety verdict). However, it lacks mention of potential limitations like data freshness or pagination, which would make it fully complete.
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 50% (state parameter described, city parameter not). The tool description does not add meaning for either parameter; it only mentions city and state generically without providing format or examples for the city parameter.
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 EPA water records for a given city, specifying the data types (systems, populations, sources, violations). It distinguishes itself from siblings like 'get_water_system' and 'find_cities' by focusing on city-level tap water data.
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 calls it 'the core tool' implying primary usage, but it does not explicitly state when to use this tool versus alternatives like 'compare_cities' or 'search'. No when-not or why-not guidance is provided.
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.
Some tools have overlapping purposes: search and search_cities both find cities by name, and fetch and get_city_water both retrieve detailed records for a city. However, descriptions differentiate them (e.g., search returns an id, search_cities returns counts and URL), so an agent can often pick correctly, but confusion is possible.
Tool names mix conventions: single-word verbs (fetch, search), verb_noun (compare_cities, find_cities), and noun_noun (coverage_stats). There is no consistent pattern, and similar tools have different naming styles (e.g., search vs search_cities).
10 tools is well-suited for querying EPA tap water data. Each tool serves a distinct purpose within the domain, and the count is neither too few (limiting functionality) nor too many (overwhelming).
The tool surface covers key operations: searching cities, retrieving records, comparing, filtering, explaining contaminants, and coverage stats. Minor gaps exist (e.g., no way to search contaminants by partial name), but core workflows are supported.