Fetch the full plain-English EPA tap-water record for a city id (e.g. 'vt/burlington') returned by search. (ChatGPT/Deep-Research compatible.)
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | City id like 'vt/burlington' (state/slug). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering safety. The description adds useful behavioral context: the output is 'full plain-English' and compatible with ChatGPT/Deep-Research. No contradictions are present.
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 extremely concise, with two sentences: the first explains the core function with an example, and the second adds a compatibility note. Every word is purposeful, and the information is front-loaded.
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 (1 parameter, no output schema, read-only), the description covers the essential aspects: input format, output type, and integration with search. It could specify that the output is a single record, but overall it is complete enough for agent use.
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 coverage is 100% for the single parameter 'id', and its description in the schema ('City id like 'vt/burlington' (state/slug).') already provides clear semantics. The tool description adds an example and context of being from search, but this is marginal beyond the schema. Baseline 3 is appropriate.
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 fetches a 'full plain-English EPA tap-water record' for a city id, with an explicit example ('vt/burlington') and linkage to the search tool. This distinguishes it from siblings like 'get_city_water' and 'compare_cities' by specifying the output format and input origin.
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 explicitly says the id is 'returned by `search`', providing clear usage context. It implies the tool is used after search to retrieve a full record, but does not explicitly state when not to use it or compare to alternatives like 'get_city_water'. However, the context is sufficient for an AI agent.
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.
Multiple tools have overlapping purposes: `search` and `search_cities` both find cities by name, and `fetch` and `get_city_water` both retrieve EPA records for a city. This creates ambiguity for an agent deciding which tool to use.
Most tools follow a verb_noun pattern (e.g., compare_cities, get_city_water), but `fetch` and `search` are single-word imperatives without an object, breaking the consistency slightly.
With 10 tools, the server is well-scoped for a data retrieval domain. Each tool has a distinct role, though some overlap could be consolidated, the count is reasonable.
Core operations (search cities, fetch records, compare, list states) are covered, but the redundancy between `fetch`/`get_city_water` suggests unclear boundaries, and there is no tool to search by water system name or list all contaminants.