Skip to main content
Glama

Search TRI Releases by Region

epa_tri_search_releases
Read-onlyIdempotent

TRI: Search Toxic Release Inventory data across facilities in a state or county, for one reporting year or, without year, every available year newest first. Returns facility name and county, TRI facility ID, EPA Registry ID (the registry_id epa_echo_get_facility takes), parent company, chemical name and TRI chemical ID with its CAS number, and the Form R one-time release quantity; set include_release_breakdown to add on-site releases by medium (air, water, land, and underground-injection) and their total, at the cost of a slower call. Quantities are in pounds; dioxin and dioxin-like compounds, which TRI has facilities report in grams, are converted and marked with reportedUnit. Records come in reporting-year order, not ranked by quantity; page through a large match with offset and nextOffset. Use to build an environmental exposure profile for an area. Use epa_tri_get_facility_releases for detailed release records for a single facility. TRI data lags ~18 months from the current calendar year.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "state": "<state>"
    },
    "name": "epa_tri_search_releases"
  }
}

Input Schema

NameRequiredDescriptionDefault
yearNoReporting year. Omit to search every available year in the state, newest reporting year first, so the first page holds the most recent filings. TRI data lags ~18 months.
limitNoNumber of release records to return in one call. Default 25; a larger value returns at most 699 and says so. Page past it with offset and nextOffset.
stateYes2-letter US state or territory code (required, e.g. "WA", "TX", "PR")
countyNoCounty name to narrow results within the state, e.g. "King". Case-insensitive partial match on the bare name, so a short name can also match a longer one (LAKE matches LAKE OF THE WOODS; check countyName on each record); a trailing "County", "Parish", "Borough", "City and Borough", "Census Area", or "Municipality" is dropped before matching. Punctuation is matched as written ("Prince George's").
offsetNoNumber of release records to skip before this page (default 0). Pass the previous call's nextOffset to continue; a value past the end returns an empty page.
chemical_idNoTRI chemical ID to match exactly, where chemical_name matches any name containing its text: a CAS Registry Number, hyphens and leading zeros optional, with a valid check digit; a TRI category code, N and three digits in any case; or a chemicalId an earlier result returned.
chemical_nameNoOptional filter to restrict results to a specific chemical (partial match, case-insensitive). Commas, apostrophes, brackets, and Greek letters are matched as written, e.g. "4,4'-Methylenedianiline".
include_release_breakdownNoAdd on-site releases by medium (air, water, land, underground injection) and their total to each record. Costs up to three extra upstream requests, made side by side, which can add about 20 seconds when EPA has not cached them.

Output Schema

NameRequiredDescriptionDefault
capNoRequested limit after the cap; present only when truncated.
errorNoPresent when the call failed. Absent on success.
shownNoPresent only when truncated.
stateNoState searched, uppercase
noticeNoPresent when a punctuated county or chemical_name filter hit its read limit first, so more matches may exist.
messageNoRecovery hint on an empty result; absent otherwise.
guidanceNoPresent when truncated: the continuing offset.
releasesNoMatching TRI records
truncatedNoTrue when more records may follow; absent on the last page.
nextOffsetNoNext offset; absent on the last page.
limitNoticeNoPresent when a smaller limit than requested applied; says why.
effectiveQueryNoThe search as sent upstream, in input names: values, match modes, and result-changing defaults, "; "-joined.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed33 schema fields changed
    • addedInput schema / properties / chemical_id
      Added value: +{
      +  "description": "TRI chemical ID to match exactly, where chemical_name matches any name containing its text: a CAS Registry Number, hyphens and leading zeros optional, with a valid check digit; a TRI category code, N and three digits in any case; or a chemicalId an earlier result returned.",
      +  "pattern": "^\\s*(?:(?:\\d{2,7}-\\d{2}-\\d|\\d{5,10}|[Nn]\\d{3}|MIXTURE|TRD SECRT|NA|INVALID)\\s*)?$",
      +  "type": "string"
      +}
    • changedInput schema / properties / include_release_breakdown / description
      Previous value: -"Add on-site releases by medium (air, water, land, underground injection) and their total to each record. Costs one extra upstream request, which can add about 20 seconds when EPA has not cached it."New value: +"Add on-site releases by medium (air, water, land, underground injection) and their total to each record. Costs up to three extra upstream requests, made side by side, which can add about 20 seconds when EPA has not cached them."
    • changedInput schema / properties / limit / default
      Previous value: -50New value: +25
    • changedInput schema / properties / limit / description
      Previous value: -"Maximum number of release records to return in one call (1–200, default 50). A larger value, up to 5,000, returns 200 with a notice. Page past it with offset and nextOffset."New value: +"Number of release records to return in one call. Default 25; a larger value returns at most 699 and says so. Page past it with offset and nextOffset."
    • changedInput schema / properties / limit / maximum
      Previous value: -5000New value: +9007199254740991
    • changedOutput schema / properties / cap / description
      Previous value: -"The limit that was applied. Present only when truncated."New value: +"Requested limit after the cap; present only when truncated."
    • changedOutput schema / properties / effectiveQuery / description
      Previous value: -"The search as the server sent it upstream, in this tool's input names: normalized values, how each text filter matched (\"=\" exact, \"contains\", \"begins with\", \"has words\"), and defaults that change what comes back. Terms are separated by \"; \"."New value: +"The search as sent upstream, in input names: values, match modes, and result-changing defaults, \"; \"-joined."
    • changedOutput schema / properties / error / properties / data / properties / reason / description
      Previous value: -"Machine-readable failure mode. Declared by this tool: `invalid_state`: state has the 2-character form but is not a US state, DC, territory, freely associated state, UM, NN, or EPA region code. `unmatchable_filter`: county or chemical_name has no letter or digit for EPA's DMAP service to match on. `filter_too_long`: county and chemical_name make a request longer than EPA's DMAP service accepts. Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `invalid_state`: state is not a US state, territory, or EPA region code. `unmatchable_filter`: county or chemical_name has no letter or digit. `filter_too_long`: county and chemical_name make the request too long. Other values are possible when a failure originates below the handler."
    • changedOutput schema / properties / guidance / description
      Previous value: -"Present when truncated: the offset that continues the search."New value: +"Present when truncated: the continuing offset."
    • changedOutput schema / properties / limitNotice / description
      Previous value: -"Present when limit was above the cap and the call returned the cap instead."New value: +"Present when a smaller limit than requested applied; says why."
    • changedOutput schema / properties / message / description
      Previous value: -"Recovery hint when no releases are found. Absent when releases are returned."New value: +"Recovery hint on an empty result; absent otherwise."
    • changedOutput schema / properties / nextOffset / description
      Previous value: -"Offset of the next page: present exactly when more records follow, absent on the last page. Pass it as offset to continue."New value: +"Next offset; absent on the last page."
    • changedOutput schema / properties / notice / description
      Previous value: -"Present when a punctuated county or chemical_name filter read its page limit before finding limit matches spelled as given, so more matching records may exist."New value: +"Present when a punctuated county or chemical_name filter hit its read limit first, so more matches may exist."
    • changedOutput schema / properties / releases / description
      Previous value: -"TRI release records for facilities in the queried state and filters"New value: +"Matching TRI records"
    • changedOutput schema / properties / releases / items / description
      Previous value: -"TRI release record for a facility-chemical-year combination"New value: +"One facility-chemical-year record; per-medium releases and their total only with include_release_breakdown"
    • addedOutput schema / properties / releases / items / properties / casNumber
      Added value: +{
      +  "description": "CAS Registry Number, hyphenated. Absent for a category code or placeholder.",
      +  "type": "string"
      +}
    • addedOutput schema / properties / releases / items / properties / chemicalId
      Added value: +{
      +  "description": "TRI chemical ID (a 10-digit zero-padded CAS number, an N-prefixed category code, or a placeholder); pass it as chemical_id for an exact match. Absent when TRI records none.",
      +  "type": "string"
      +}
    • changedOutput schema / properties / releases / items / properties / chemicalName / description
      Previous value: -"Chemical name as reported to TRI"New value: +"Name as reported to TRI"
    • changedOutput schema / properties / releases / items / properties / countyName / description
      Previous value: -"County as TRI records the facility's location (e.g. \"KING\", \"CALCASIEU PARISH\"). The county filter is a partial match, so a short name can also match a longer one (LAKE matches LAKE OF THE WOODS); check this field to keep only the county you meant."New value: +"As TRI records it; county matches partially, so check this field"
    • changedOutput schema / properties / releases / items / properties / facilityId / description
      Previous value: -"TRI facility identifier"New value: +"TRI facility ID"
    • changedOutput schema / properties / releases / items / properties / oneTimeReleaseInLbs / description
      Previous value: -"Form R Section 8.8 one-time release quantity in pounds (remedial actions, catastrophic events, and other one-time events not associated with production). It is already counted in the per-medium releases and the off-site transfers, so it is never added to them."New value: +"Form R Section 8.8 one-time release quantity in pounds; already counted in the per-medium releases and off-site transfers, so never added to them."
    • changedOutput schema / properties / releases / items / properties / parentCompany / description
      Previous value: -"Parent company as TRI standardizes its name. Absent when TRI records no parent company (its placeholder is NA)."New value: +"As TRI standardizes it; absent when TRI records none (its NA placeholder)"
    • changedOutput schema / properties / releases / items / properties / registryId / description
      Previous value: -"12-digit EPA Facility Registry Service ID; pass it as registry_id to epa_echo_get_facility for the facility's compliance profile. Absent when TRI records none."New value: +"12-digit FRS Registry ID; pass it as registry_id to epa_echo_get_facility. Absent when TRI records none."
    • changedOutput schema / properties / releases / items / properties / releasesToAirInLbs / description
      Previous value: -"On-site air releases (fugitive + stack emissions) in pounds, summed across air release types for this submission. Only with include_release_breakdown."New value: +"On-site fugitive + stack air, in pounds"
    • changedOutput schema / properties / releases / items / properties / releasesToLandInLbs / description
      Previous value: -"On-site land releases in pounds — landfills, land treatment, surface impoundment, and other on-site disposal, summed for this submission. Only with include_release_breakdown."New value: +"On-site, disposal included, in pounds"
    • changedOutput schema / properties / releases / items / properties / releasesToUndergroundInjectionInLbs / description
      Previous value: -"On-site releases via underground injection wells in pounds, summed across injection well classes for this submission. Only with include_release_breakdown."New value: +"On-site injection wells, all classes, in pounds"
    • changedOutput schema / properties / releases / items / properties / releasesToWaterInLbs / description
      Previous value: -"On-site releases to surface water in pounds, summed across all reported outfalls for this submission. Only with include_release_breakdown."New value: +"On-site, all outfalls, in pounds"
    • changedOutput schema / properties / releases / items / properties / reportedUnit / description
      Previous value: -"Present as \"grams\" when TRI had the facility report this chemical in grams (dioxin and dioxin-like compounds); its quantities here are converted to pounds (1 lb = 453.59237 g). Absent for chemicals reported in pounds."New value: +"\"grams\" when TRI has the chemical reported in grams (dioxin and dioxin-like compounds); quantities here are converted to pounds (1 lb = 453.59237 g). Absent otherwise."
    • changedOutput schema / properties / releases / items / properties / reportingYear / description
      Previous value: -"Year of the TRI submission"New value: +"TRI reporting year"
    • changedOutput schema / properties / releases / items / properties / totalOnSiteReleasesInLbs / description
      Previous value: -"Sum of the per-medium on-site releases present on this record (Form R Sections 5.1–5.5.4), in pounds. A medium TRI recorded only as a range code is left out, as it is from the per-medium fields; TRI's published on-site total counts a range at its midpoint, so it can be higher. Only with include_release_breakdown, and absent when no medium has a quantity."New value: +"Sum of the per-medium fields present, in pounds; absent when none has a quantity. Media reported only as a range code are left out; TRI's published total counts their midpoint, so it can be higher."
    • changedOutput schema / properties / shown / description
      Previous value: -"Number of release records returned. Present only when truncated."New value: +"Present only when truncated."
    • changedOutput schema / properties / state / description
      Previous value: -"State queried, as the search sent it (uppercase code)"New value: +"State searched, uppercase"
    • changedOutput schema / properties / truncated / description
      Previous value: -"True when more release records may follow this page; nextOffset continues it. Absent on the last page."New value: +"True when more records may follow; absent on the last page."
  2. Changed27 schema fields changed
    • changedInput schema / properties / county / description
      Previous value: -"County name to narrow results within the state, e.g. \"King\". Case-insensitive partial match on the bare name, so a short name can also match a longer one (LAKE matches LAKE OF THE WOODS; check countyName on each record); a trailing \"County\", \"Parish\", or \"Borough\" is dropped before matching. Punctuation is matched as written (\"Prince George's\")."New value: +"County name to narrow results within the state, e.g. \"King\". Case-insensitive partial match on the bare name, so a short name can also match a longer one (LAKE matches LAKE OF THE WOODS; check countyName on each record); a trailing \"County\", \"Parish\", \"Borough\", \"City and Borough\", \"Census Area\", or \"Municipality\" is dropped before matching. Punctuation is matched as written (\"Prince George's\")."
    • changedInput schema / properties / include_release_breakdown / description
      Previous value: -"Add routine on-site releases by medium (air, water, land, underground injection) to each record. Costs one extra upstream request, which can add about 20 seconds when EPA has not cached it."New value: +"Add on-site releases by medium (air, water, land, underground injection) and their total to each record. Costs one extra upstream request, which can add about 20 seconds when EPA has not cached it."
    • changedInput schema / properties / limit / description
      Previous value: -"Maximum number of release records to return (1–200)"New value: +"Maximum number of release records to return in one call (1–200, default 50). A larger value, up to 5,000, returns 200 with a notice. Page past it with offset and nextOffset."
    • changedInput schema / properties / limit / maximum
      Previous value: -200New value: +5000
    • addedInput schema / properties / offset
      Added value: +{
      +  "default": 0,
      +  "description": "Number of release records to skip before this page (default 0). Pass the previous call's nextOffset to continue; a value past the end returns an empty page.",
      +  "maximum": 9007199254740991,
      +  "minimum": 0,
      +  "type": "integer"
      +}
    • changedInput schema / properties / state / description
      Previous value: -"2-letter US state abbreviation (required, e.g. \"WA\", \"TX\")"New value: +"2-letter US state or territory code (required, e.g. \"WA\", \"TX\", \"PR\")"
    • removedInput schema / properties / state / maxLength
      Removed value: -2
    • removedInput schema / properties / state / minLength
      Removed value: -2
    • addedInput schema / properties / state / pattern
      Added value: +"^\\s*[A-Za-z0-9]{2}\\s*$"
    • changedInput schema / properties / year / description
      Previous value: -"Reporting year. Omit to search every available year in the state, newest reporting year first, so limit keeps the most recent filings. TRI data lags ~18 months."New value: +"Reporting year. Omit to search every available year in the state, newest reporting year first, so the first page holds the most recent filings. TRI data lags ~18 months."
    • addedOutput schema / properties / effectiveQuery
      Added value: +{
      +  "description": "The search as the server sent it upstream, in this tool's input names: normalized values, how each text filter matched (\"=\" exact, \"contains\", \"begins with\", \"has words\"), and defaults that change what comes back. Terms are separated by \"; \".",
      +  "type": "string"
      +}
    • changedOutput schema / properties / error / properties / data / properties / reason / description
      Previous value: -"Machine-readable failure mode."New value: +"Machine-readable failure mode. Declared by this tool: `invalid_state`: state has the 2-character form but is not a US state, DC, territory, freely associated state, UM, NN, or EPA region code. `unmatchable_filter`: county or chemical_name has no letter or digit for EPA's DMAP service to match on. `filter_too_long`: county and chemical_name make a request longer than EPA's DMAP service accepts. Other values are possible when a failure originates below the handler."
    • addedOutput schema / properties / error / properties / data / properties / reason / examples
      Added value: +[
      +  "invalid_state",
      +  "unmatchable_filter",
      +  "filter_too_long"
      +]
    • addedOutput schema / properties / guidance
      Added value: +{
      +  "description": "Present when truncated: the offset that continues the search.",
      +  "type": "string"
      +}
    • addedOutput schema / properties / limitNotice
      Added value: +{
      +  "description": "Present when limit was above the cap and the call returned the cap instead.",
      +  "type": "string"
      +}
    • addedOutput schema / properties / nextOffset
      Added value: +{
      +  "description": "Offset of the next page: present exactly when more records follow, absent on the last page. Pass it as offset to continue.",
      +  "type": "number"
      +}
    • addedOutput schema / properties / releases / items / properties / oneTimeReleaseInLbs
      Added value: +{
      +  "description": "Form R Section 8.8 one-time release quantity in pounds (remedial actions, catastrophic events, and other one-time events not associated with production). It is already counted in the per-medium releases and the off-site transfers, so it is never added to them.",
      +  "type": "number"
      +}
    • addedOutput schema / properties / releases / items / properties / parentCompany
      Added value: +{
      +  "description": "Parent company as TRI standardizes its name. Absent when TRI records no parent company (its placeholder is NA).",
      +  "type": "string"
      +}
    • addedOutput schema / properties / releases / items / properties / registryId
      Added value: +{
      +  "description": "12-digit EPA Facility Registry Service ID; pass it as registry_id to epa_echo_get_facility for the facility's compliance profile. Absent when TRI records none.",
      +  "type": "string"
      +}
    • changedOutput schema / properties / releases / items / properties / releasesToAirInLbs / description
      Previous value: -"On-site routine air releases (fugitive + stack emissions) in pounds, summed across air release types for this submission. Only with include_release_breakdown."New value: +"On-site air releases (fugitive + stack emissions) in pounds, summed across air release types for this submission. Only with include_release_breakdown."
    • changedOutput schema / properties / releases / items / properties / releasesToLandInLbs / description
      Previous value: -"On-site routine land releases in pounds — landfills, land treatment, surface impoundment, and other on-site disposal, summed for this submission. Only with include_release_breakdown."New value: +"On-site land releases in pounds — landfills, land treatment, surface impoundment, and other on-site disposal, summed for this submission. Only with include_release_breakdown."
    • changedOutput schema / properties / releases / items / properties / releasesToUndergroundInjectionInLbs / description
      Previous value: -"On-site routine releases via underground injection wells in pounds, summed across injection well classes for this submission. Only with include_release_breakdown."New value: +"On-site releases via underground injection wells in pounds, summed across injection well classes for this submission. Only with include_release_breakdown."
    • changedOutput schema / properties / releases / items / properties / releasesToWaterInLbs / description
      Previous value: -"On-site routine releases to surface water in pounds, summed across all reported outfalls for this submission. Only with include_release_breakdown."New value: +"On-site releases to surface water in pounds, summed across all reported outfalls for this submission. Only with include_release_breakdown."
    • addedOutput schema / properties / releases / items / properties / totalOnSiteReleasesInLbs
      Added value: +{
      +  "description": "Sum of the per-medium on-site releases present on this record (Form R Sections 5.1–5.5.4), in pounds. A medium TRI recorded only as a range code is left out, as it is from the per-medium fields; TRI's published on-site total counts a range at its midpoint, so it can be higher. Only with include_release_breakdown, and absent when no medium has a quantity.",
      +  "type": "number"
      +}
    • removedOutput schema / properties / releases / items / properties / totalReleasesInLbs
      Removed value: -{
      -  "description": "TRI one-time / non-routine release quantity in pounds (spills, accidents) — a distinct TRI category, NOT the sum of the per-medium routine releases below.",
      -  "type": "number"
      -}
    • changedOutput schema / properties / state / description
      Previous value: -"State queried"New value: +"State queried, as the search sent it (uppercase code)"
    • changedOutput schema / properties / truncated / description
      Previous value: -"True when the result list was capped at the limit — more records may exist. Absent below the limit."New value: +"True when more release records may follow this page; nextOffset continues it. Absent on the last page."
  3. Added

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already declare readOnly/openWorld/idempotent, but the description adds genuinely non-structural behavior: the ~18-month TRI reporting lag, pounds as the unit with gram-reported dioxin converted and flagged via reportedUnit, results ordered by reporting year rather than ranked by quantity, and the silent 699-record cap behind limit. The ~20-second cost of include_release_breakdown is disclosed before the agent opts in.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with scope and cost/benefit tradeoffs, and no sentence is filler. However, the long enumeration of return fields (facility name, county, TRI ID, registry ID, parent company, chemical name, chemical ID, CAS, quantity) duplicates an output schema that already exists, so some of that space does not earn its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an 8-parameter, open-world, paginated search tool, everything an agent needs to call it correctly is present: required state, year-omission semantics, the limit cap and paging path, unit conversions, and the sibling to use for facility-level detail. The output schema and annotations cover the remaining return-shape and safety questions.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

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 earns more by adding cross-field meaning the schema cannot carry — that registry_id is the key epa_echo_get_facility accepts, that include_release_breakdown buys medium-level breakdowns for latency, and that offset pairs with nextOffset for paging. It does not restate the county or chemical_id matching rules, correctly leaving those to the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Names a specific verb and resource (search TRI release records) plus the exact scope axes — state, optional county, one reporting year or all years. The last-line routing ('Use epa_tri_get_facility_releases for detailed release records for a single facility') makes it distinguishable from its closest sibling without opening either schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives a positive use case ('build an environmental exposure profile for an area') and explicitly names the alternative tool plus the condition that selects it (single facility → epa_tri_get_facility_releases). It also flags the year-omission tradeoff and the include_release_breakdown cost, so the agent can choose a call shape, not just a tool.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.