GroundTruth - Environmental Records

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It honestly discloses the approximate nature of matching, the fact that service boundaries are not public, and suggests the user's water bill as a reliable source. This is valuable transparency beyond what the schema provides, though it does not cover potential edge cases or response details.

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: two sentences with no redundant filler. The first sentence states the core purpose, and the second adds a crucial caveat. Every word earns its place.

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 simple 3-parameter lookup with no output schema, the description conveys the essential result content (public water systems with violation summaries) and the approximation caveat. It does not explain the response structure or specific fields, but the level of detail is adequate for an agent to understand expected outcomes.

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?

The input schema already provides 100% coverage for all three parameters (state, city, county), so the baseline is 3. The description adds minimal extra meaning beyond the schema, only mentioning the combination of state plus county and/or city. It does not elaborate on parameter formats or edge cases.

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 identifies the tool as returning public water systems and their health-based SDWA violation summaries for a given state, county, and/or city. The specific resource type and domain are clear, but it lacks an explicit verb like 'list' or 'find.' It distinguishes from the sibling tool 'environment_near' by focusing on drinking water systems.

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 implies the tool should be used to look up water utilities based on location, and the caveat about approximate matching provides context on how to interpret results. However, it does not explicitly state when to prefer this tool over 'environment_near' or mention any exclusions. The advice to consult the water bill is a useful guidance element.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It does this well by explaining the score scale (0-1, higher = favorable), null behavior for unscorable layers, the no_coverage flag for machine-readable placeholder detection, the instruction to relay caveats verbatim, and specific coverage regions per layer. It also notes the geocoding mechanism. A few aspects like error handling or rate limits are not covered, but the description is thorough for its purpose.

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 one dense paragraph, but it is well-structured: it leads with the core function and layer list, then scoring rules, coverage details, and finally input options. Every sentence adds value, and the information is front-loaded with the most critical details (What it does and the score scale). It could be slightly more scannable with bullet points, but it remains concise given the amount of essential information.

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?

The tool has no output schema, so the description must convey what to expect in the response. It does this by explaining the score range, null handling, and the no_coverage flag, which gives a clear picture of the result structure. It also details coverage limitations and input alternatives, making the tool callable without further ambiguity. Missing details like a literal output example or error behaviors are minor gaps given the clarity provided.

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?

The schema descriptions for lat, lon, and address are simple coordinate/address definitions with 100% schema description coverage, giving a baseline of 3. The tool description adds critical semantics by stating that EITHER an address OR lat/lon coordinates must be passed, and that the address is geocoded via the US Census geocoder. This clarifies the mutual exclusivity and the geocoding behavior, which is not present in the schema.

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's function: it computes due-diligence layer scores for a US location across a specific list of environmental and social factors. The verb 'address' combined with the explicit resource ('due-diligence layer scores') and the enumerated layers makes the purpose unambiguous. It also distinguishes itself from siblings by listing its distinct scope (e.g., schools, crime, climate) whereas siblings likely focus on narrower domains like water or nearby features.

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 clear usage context: it specifies the input alternatives (address vs. lat/lon), the geocoding method, and detailed coverage limitations for each layer. However, it does not explicitly mention alternatives or when not to use this tool versus the sibling tools (e.g., drinking_water, environment_near). The implications are clear from the scope, but explicit exclusions or comparison are absent.

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

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

With no annotations, the description carries the transparency burden. It discloses the geocoding behavior via US Census and the types of records, but it does not mention what happens if both address and coordinates are provided, output format, pagination, or potential errors. This is partial disclosure.

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 concise sentences: the first states purpose and scope, the second gives input instructions. No fluff or redundant content; every phrase earns its place.

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?

Despite having no output schema or annotations, the description covers the main aspects: what records are returned, how to specify location, and the radius parameter (implicitly). It lacks details on default/max radius and return structure, but the schema covers those, making it adequate for a simple query tool.

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%, so the baseline is 3. The description adds meaning by explaining the address geocoding mechanism and explicitly stating that address and lat/lon are alternatives, which clarifies the conditional requirement not present in the schema.

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's function: retrieving federal environmental records (Superfund/NPL, TRI, noncomplying facilities) within a radius of a US location. It names specific data sources and distinguishes itself from the sibling drinking_water tool by domain.

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 says when to use the tool (for environmental records near a location) and provides usage instructions for the two input modes (address or lat/lon). It does not explicitly mention the sibling or state exclusions, but the context is clear.

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