chemical_accident_searchSearch EPA RMP hazardous-chemical facilities (Clean Air Act 112(r)) by facility or parent-company name. Returns each facility's chemical-accident count + location. ~99k facilities — the chemical-plant accident ledger EPA keeps FOIA-only (releases, fires, explosions, deaths).
| Name | Required | Description | Default |
|---|---|---|---|
| q | Yes | Facility or parent-company name (>=2 chars) | |
| limit | No | Max results (default 25, max 100) |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already establish read-only, idempotent, non-destructive, closed-world behavior, so the bar is lower. The description still adds real value beyond the structured fields: dataset size (~99k facilities), the FOIA-only provenance, and the semantic meaning of the counts (releases, fires, explosions, deaths).
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?
Three sentences, front-loaded with the verb and resource, then the return shape, then the scale/provenance. Dense and mostly waste-free, though the closing 'ledger EPA keeps FOIA-only' phrase is more color than operational detail.
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?
With no output schema and only annotations covering safety, the description correctly compensates by naming the returned fields (accident count, location) and setting expectations about dataset breadth. Minor gaps remain around result ordering and pagination semantics, but nothing needed to invoke it is missing.
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 both parameters (q, limit) are already documented in the schema. The description restates the facility/parent-company search key and adds nothing about matching behavior (prefix vs. substring, case sensitivity) or the limit, so baseline 3 applies.
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 gives a specific verb (Search) and resource (EPA RMP hazardous-chemical facilities under Clean Air Act 112(r)) and states the lookup key (facility or parent-company name) plus what is returned (accident count + location). It is clear what the tool does, but it never names the obvious sibling `chemical_accident_worst`, so the agent must infer the split between name-lookup and ranking.
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?
Usage is implied by the framing — it is a name/keyword lookup rather than a ranked list — but there is no explicit when-to-use/when-not statement and no named alternative for cases like 'show me the worst facilities.' Minimum-viable guidance only.
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.