openfec-mcp-server
Server Details
Access FEC campaign finance data. Query data about candidates, money trails, and election filings.
- Status
- Healthy
- Uptime
- 100.0% over 37 days
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- cyanheads/openfec-mcp-server
- GitHub Stars
- 2
- Server Listing
- @cyanheads/openfec-mcp-server
TDQS
Scored across 12 tools
Each tool targets a distinct FEC dataset or subdomain, but the four money-movement tools (contributions, disbursements, expenditures, coordinated expenditures) could be confused despite clear descriptions distinguishing Schedule A/B/E/F. The lookup vs search split is clear, and legal/calendar/elections tools are unambiguous.
All tools follow the uniform openfec_verb_noun pattern with consistent verbs: get for single records, lookup for reference lookups, and search for dataset queries. The naming is predictable and scannable across all 12 tools.
12 tools is well within the ideal range for a domain-specific read-only API. Each tool maps to a real FEC data category without redundancy, giving the server broad coverage without bloat.
The surface covers the major FEC datasets: candidates, committees, contributions, disbursements, independent and coordinated expenditures, filings, legal documents, calendar events, elections, and committee totals. No obvious dead ends or missing core operations for a read-only campaign finance lookup server.
Available Tools
12 toolsopenfec_get_committee_totalsOpenfec Get Committee TotalsARead-onlyIdempotentInspect
Get pre-aggregated committee financial totals — receipts, disbursements, cash on hand, debts, and the itemized/unitemized breakdown — without paginating Schedule A. Use mode "single" (the default) with a committee_id for one committee's totals, one row per two-year cycle it has filed. Use mode "by_entity_type" to rank or screen every committee of one type (presidential, pac, party, pac-party, house-senate, ie-only) by state, designation, or a receipts/disbursements threshold.
| Name | Required | Description | Default |
|---|---|---|---|
| mode | No | Query mode. "single" returns one committee's totals, one row per cycle. "by_entity_type" returns a page of committees of one entity type, filterable and sortable across committees. | single |
| page | No | Page number (1-indexed). Read pagination.pages in the response to see how many pages exist — a long-running committee can have more cycles than one page holds. | |
| sort | No | Sort field. A "-" prefix sorts descending: "-receipts" ranks the biggest fundraisers first in by_entity_type mode, "-cycle" puts a committee's most recent cycle first in single mode. | |
| cycle | No | Two-year election cycle (e.g., 2024). Even years only. Omit in single mode to get every cycle the committee has filed. | |
| per_page | No | Results per page. | |
| entity_type | No | Committee entity type for the grouped search. Required in by_entity_type mode. house-senate covers both chambers as one group; ie-only is committees that report only independent expenditures. | |
| committee_id | No | Committee ID (e.g., C00703975). Get IDs from openfec_search_committees results. Required in single mode; in by_entity_type mode it narrows the grouped search to that one committee. | |
| max_receipts | No | Maximum total receipts in dollars. by_entity_type mode only. | |
| min_receipts | No | Minimum total receipts in dollars. by_entity_type mode only. | |
| committee_type | No | Committee type code — H (House), S (Senate), P (Presidential), O (Super PAC), N/Q (PAC), X/Y (party). by_entity_type mode only. | |
| committee_state | No | Two-letter state code of the committee. by_entity_type mode only. | |
| max_disbursements | No | Maximum total disbursements in dollars. by_entity_type mode only. | |
| min_disbursements | No | Minimum total disbursements in dollars. by_entity_type mode only. | |
| organization_type | No | Sponsoring organization type — C (corporation), L (labor), M (membership), T (trade), V (cooperative), W (corporation without capital stock). by_entity_type mode only. | |
| committee_designation | No | Committee designation — A (authorized), B (lobbyist PAC), D (leadership PAC), J (joint fundraiser), P (principal campaign), U (unauthorized). by_entity_type mode only. |
Output Schema
| Name | Required | Description |
|---|---|---|
| mode | No | Query mode as the server resolved it. Rows mean different things by mode — single rows are cycles of one committee, by_entity_type rows are different committees — so read this rather than inferring from the fields present. |
| error | No | Present when the call failed. Absent on success. |
| notice | No | Guidance when the response carries no totals: how to broaden a search that matched nothing, or which requested position ran out when totals did match. |
| results | No | Committee totals result set; one row per cycle in single mode, one row per committee in by_entity_type mode. |
| pagination | No | Page-based pagination metadata. |
| totalCount | No | Total matching totals rows before pagination. |
| search_criteria | No | Echo of the search filters this call applied, as the server parsed them, minus paging arguments. Always present — compare it against what you sent to confirm every filter was honoured. |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already mark the operation as read-only and idempotent, so the description can focus on additional behavior. It discloses that results are pre-aggregated, that single mode returns one row per two-year cycle, and that by_entity_type mode supports ranking across committees. This goes beyond the annotations without contradicting them.
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 tightly written sentences front-load the tool's purpose and data contents, then give mode usage guidance. Every sentence earns its place and no words are wasted.
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 15-parameter tool with two modes, the description provides enough high-level orientation: how to select a mode, what each mode returns, and how this tool relates to Schedule A data. The detailed input schema and output schema cover the remaining specifics, so nothing needed for correct invocation 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 the baseline is 3 even without additional param detail in the tool description. The description adds helpful mode-level framing, but it mostly restates the schema's mode and committee_id semantics rather than adding new parameter information.
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 opens with a specific verb and resource: 'Get pre-aggregated committee financial totals' and enumerates the exact data fields returned. It also distinguishes this tool from raw Schedule A lookup by the phrase 'without paginating Schedule A.'
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 explains when to use each mode: 'single' for one committee's totals and 'by_entity_type' for ranking or screening committees by type, state, or thresholds. It also states the default mode and that committee_id is the key input for the single mode.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
openfec_get_legal_documentOpenfec Get Legal DocumentARead-onlyIdempotentInspect
Fetch one FEC legal document in full — advisory opinion, MUR, ADR, administrative fine, or statute — by its type and number. openfec_search_legal replaces each result's documents array with a count and category summary and cuts every commission vote down to a date and a 200-character action; this returns the record untouched. doc_type is the plural form of the document_type discriminator on a search result (advisory_opinion becomes advisory_opinions, mur becomes murs, adr becomes adrs, admin_fine becomes admin_fines, statute becomes statutes), and no is that result's no field — every document type carries it, and advisory opinions repeat it as ao_no.
| Name | Required | Description | Default |
|---|---|---|---|
| no | Yes | Document number, copied from the no field of the matching openfec_search_legal result. Advisory opinions are year-serial (e.g. "2024-01", also repeated as ao_no); murs, adrs, and admin_fines are digit strings (e.g. "8363"); statutes are U.S. Code section numbers (e.g. "30123"). | |
| doc_type | Yes | Legal document type, always plural. openfec_search_legal reports the singular form in each result document_type — advisory_opinion, mur, adr, admin_fine, statute — so add an "s" to get the value this field wants. |
Output Schema
| Name | Required | Description |
|---|---|---|
| error | No | Present when the call failed. Absent on success. |
| document | No | The complete legal document record. Carries the full documents array that openfec_search_legal replaces with a count and category summary, and the complete commission_votes entries it reduces to a vote date and a truncated action, alongside the dispositions and the scalar and date fields (name, type, url, penalty and determination amounts, case dates). Fields present vary by document type. |
| search_criteria | No | Echo of the search filters this call applied, as the server parsed them, minus paging arguments. Always present — compare it against what you sent to confirm every filter was honoured. |
| attachedDocumentCount | No | Number of related filings in the record documents array. Compare against the document_count openfec_search_legal reported for the same record. |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations readOnlyHint/idempotentHint already establish safety, so the description earns credit for adding context: it states the tool returns the record untouched and explains how search_legal's output is transformed. It doesn't cover error/missing-record behavior, but this is not a serious gap given the annotations and output schema.
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 dense sentences, front-loaded with the core purpose, then a sibling comparison, then parameter conventions. No filler or repetition of schema enums.
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 two-parameter read tool with a full output schema and strong annotations, the description covers purpose, selection criteria, parameter derivation, and return behavior. Nothing critical an agent needs to call it correctly is absent.
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 already documents both params at 100% coverage, so the baseline is 3; the description adds value by explaining the plural/singular mapping from search results and noting that no is carried by every type (and repeated as ao_no for advisory opinions). This enriches the semantics of both fields beyond 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?
States a specific verb ('Fetch'), a precise resource ('one FEC legal document in full'), and enumerates the five document types it accepts. It also distinguishes itself from openfec_search_legal, so an agent can tell the two apart without inspecting schemas.
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?
Names openfec_search_legal and contrasts its truncating behavior with this tool's untouched full-record return, effectively telling an agent to use this when the full record is needed. It also explains how to derive doc_type from a search result's document_type, which is direct usage guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
openfec_lookup_calendarOpenfec Lookup CalendarARead-onlyIdempotentInspect
Look up FEC calendar events, filing deadlines, and election dates. Use to find upcoming filing windows for a committee, locate when a federal election occurred, or scope FEC events by date range and category.
| Name | Required | Description | Default |
|---|---|---|---|
| mode | No | events = FEC calendar events. filing_deadlines = report due dates. election_dates = upcoming/past elections. | events |
| page | No | Page number (1-indexed). Default 1. | |
| state | No | Two-letter state code (e.g., AZ, CA). Primarily for election_dates mode. | |
| office | No | Office sought (H=House, S=Senate, P=President). Election dates mode. | |
| category | No | Calendar category ID. 20=Commission Meetings, 21=Reporting Deadlines, 22=Conferences and Outreach, 23=AOs and Rules, 24=Other, 25=Quarterly, 26=Monthly, 27=Pre and Post-Elections, 28=EC Periods, 29=IE Periods, 32=Open Meetings, 33=Conferences, 34=Roundtables, 36=Election Dates, 37=Federal Holidays, 38=FEA Periods, 39=Executive Sessions, 40=Public Hearings. Events mode only. | |
| max_date | No | Latest date (YYYY-MM-DD). | |
| min_date | No | Earliest date (YYYY-MM-DD). | |
| per_page | No | Results per page. Default 20, max 100. | |
| description | No | Full-text event description search. Events mode. | |
| report_type | No | Report type code (e.g. "Q1", "Q2"). Filing deadlines mode only. | |
| report_year | No | Report year. Filing deadlines mode. | |
| election_year | No | Election year. Election dates mode. |
Output Schema
| Name | Required | Description |
|---|---|---|
| mode | No | Query mode as the server resolved it. Each mode reads a different FEC dataset with its own row shape — calendar events, report due dates, or election dates — so read this rather than inferring the dataset from the fields present. |
| error | No | Present when the call failed. Absent on success. |
| notice | No | Guidance when the response carries no calendar entries: how to broaden a search that matched nothing, or which requested position ran out when entries did match. |
| results | No | Calendar result set; events, filing deadlines, or election dates depending on mode. |
| pagination | No | Page-based pagination metadata. |
| totalCount | No | Total matching calendar entries before pagination. |
| search_criteria | No | Echo of the search filters this call applied, as the server parsed them, minus paging arguments. Always present — compare it against what you sent to confirm every filter was honoured. |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint and idempotentHint, so the description only needs to confirm the read-only nature and add scope; 'Look up' does that. It does not disclose pagination behavior or any operational details, but with safe read-only annotations the gap is minor.
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?
Two sentences, no filler, no repeating schema content. The primary purpose is front-loaded and the use cases appear in the second sentence, making it easy to scan.
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 100% schema coverage, the schema already explains each parameter, and the output schema handles return values. The description covers the main use cases; the only meaningful gap is not routing the agent away from openfec_lookup_elections when pure election lookups are needed.
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 the schema carries the detailed meaning of mode, category, date filters, and report type. The description adds only a general mention of date range and category, which maps to existing parameters but provides no new semantic information.
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 names a specific resource (FEC calendar events, filing deadlines, election dates) and provides concrete use cases, so an agent understands what the tool retrieves. It is distinguishable from candidate/committee search tools, though it does not explicitly differentiate itself from the sibling openfec_lookup_elections despite overlapping election-date functionality.
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 gives explicit context with 'Use to find upcoming filing windows... locate when a federal election occurred, or scope FEC events by date range and category.' It lacks exclusions or alternatives such as pointing to openfec_lookup_elections, but the situations described are clear enough for common selection decisions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
openfec_lookup_electionsOpenfec Lookup ElectionsBRead-onlyIdempotentInspect
Look up federal election races and candidate financial summaries. Find who's running in a race with fundraising totals, or get an aggregate race summary.
| Name | Required | Description | Default |
|---|---|---|---|
| zip | No | ZIP code — finds races covering this ZIP. Search mode only. | |
| mode | No | search = candidates in a race with financial totals. summary = aggregate race financial summary. | search |
| page | No | Page number (1-indexed). Search mode only; explicit page is rejected in summary mode. Defaults to 1 for search. | |
| cycle | Yes | Election cycle year (even years only, e.g. 2024). | |
| state | No | Two-letter US state code (e.g., AZ, CA). Required for senate/house unless zip is provided. | |
| office | Yes | Office sought: H=House, S=Senate, P=President. | |
| district | No | Two-digit district number (e.g. "07"). Required for house unless zip is provided. | |
| per_page | No | Results per page. Search mode only; defaults to 20. | |
| election_full | No | Expand to full election period (4yr president, 6yr senate, 2yr house). Defaults to true when omitted; a ZIP-scoped search rejects it, since that endpoint has no such parameter. Carries no schema default, so an explicit value is distinguishable from an omission. |
Output Schema
| Name | Required | Description |
|---|---|---|
| mode | No | Query mode as the server resolved it. Row shapes differ by mode — search rows are per-candidate financial records, summary is one aggregate race row — so read this rather than inferring the shape from the fields present. |
| error | No | Present when the call failed. Absent on success. |
| notice | No | Guidance when the response carries no election results: how to broaden a search that matched nothing, or which requested position ran out when results did match. |
| results | No | Election race result set; candidate financial rows in search mode, a single aggregate summary row in summary mode. |
| pagination | No | Page-based pagination metadata. |
| totalCount | No | Total matching candidates or race summaries. |
| search_criteria | No | Echo of the search filters this call applied, as the server parsed them, minus paging arguments. Always present — compare it against what you sent to confirm every filter was honoured. |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and idempotentHint=true, so the safety profile is covered. The description adds the behavioral distinction between search and summary modes, and the schema adds mode-specific constraints (e.g., page rejected in summary mode, ZIP-scoped search rejects election_full). However, the description itself doesn't disclose these mode-specific behaviors; they live in the schema. No contradiction with 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?
Two sentences, front-loaded with the core purpose and a brief mode distinction. It is concise and readable, though the second sentence could arguably be folded into the first. 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?
The tool has 9 parameters, an output schema, and mode-specific constraints. The description covers the high-level purpose and the two modes, but it doesn't mention the ZIP vs state/district routing logic or the mode-specific parameter rejections, which are important for correct invocation. The schema carries most of the burden, and the output schema exists, so this is adequate but not 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 100%, so the schema already documents all 9 parameters. The description adds a high-level framing ('search = candidates in a race with financial totals, summary = aggregate race financial summary') that helps interpret mode, but it doesn't add meaning beyond the schema for most parameters. 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 states a specific verb ('look up') and resource ('federal election races and candidate financial summaries'), and distinguishes two modes: finding who's running with fundraising totals, or getting an aggregate race summary. It doesn't explicitly name a sibling to differentiate from, but the resource and modes are clear enough to separate it from the sibling search tools.
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 usage by describing the two modes ('search' vs 'summary') and what each returns, but it doesn't explicitly state when to prefer this tool over siblings like openfec_search_candidates. The schema provides some guidance (e.g., zip vs state/district requirements), but the description itself offers no when-to-use or when-not-to-use guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
openfec_search_candidatesOpenfec Search CandidatesARead-onlyIdempotentInspect
Find federal candidates by name, state, office, party, or cycle. Retrieve a specific candidate by FEC ID with financial totals. Candidate IDs start with H (House), S (Senate), or P (President) followed by exactly eight letters or digits.
| Name | Required | Description | Default |
|---|---|---|---|
| page | No | Search-results page number (1-indexed). Defaults to 1 on the search path. | |
| cycle | No | Two-year election cycle (even year, e.g., 2024). | |
| party | No | Three-letter party code (e.g., DEM, REP, LIB). | |
| query | No | Full-text candidate name search. | |
| state | No | Two-letter US state code (e.g., AZ, CA). | |
| office | No | Filter by office: H=House, S=Senate, P=President. | |
| district | No | Two-digit district number for House candidates. | |
| per_page | No | Search results per page. Defaults to 20 on the search path. | |
| candidate_id | No | FEC candidate ID: H, S, or P followed by exactly eight letters or digits (e.g., P00003392, H2CO07170). Get IDs from openfec_search_candidates results. When provided, returns a single candidate with full detail. | |
| election_year | No | Specific election year the candidate ran in. | |
| include_totals | No | Include financial totals (receipts, disbursements, cash on hand). Defaults to true when fetching by candidate_id. | |
| candidate_status | No | Candidate status: C=present, F=future, N=not yet, P=prior. | |
| has_raised_funds | No | Only candidates whose committee has received receipts. | |
| incumbent_challenge | No | Incumbent status: I=incumbent, C=challenger, O=open seat. |
Output Schema
| Name | Required | Description |
|---|---|---|
| error | No | Present when the call failed. Absent on success. |
| notice | No | Guidance when the response carries no candidates: how to broaden a search that matched nothing, or which requested position ran out when candidates did match. |
| totals | No | Financial totals (receipts, disbursements, cash_on_hand) when include_totals is true. One row per candidate per cycle. |
| candidates | No | Candidate result set; one record per match. |
| pagination | No | Page-based pagination metadata. |
| totalCount | No | Total matching candidates before pagination. |
| missing_totals | No | Candidates whose financial totals were not retrieved because the totals fetch hit its page cap. Re-query each one on its own with candidate_id to get its totals. |
| search_criteria | No | Echo of the search filters this call applied, as the server parsed them, minus paging arguments. Always present — compare it against what you sent to confirm every filter was honoured. |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint and idempotentHint, so the safety profile is covered. The description adds the ID-prefix rule and that a specific ID returns financial totals, but much of this is also present in the schema; no rate limits, pagination behavior, or edge-case semantics are disclosed.
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?
Two sentences front-load the core search behavior, then add the important ID-lookup variant and ID format rule. There is no filler or redundant explanation; every sentence 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?
Given 14 parameters, a fully described schema, and an output schema, the description gives enough high-level orientation: what candidates are, how to filter, and how to do exact ID lookup. It could add a brief note on when the ID-lookup path is preferable, but the schema and annotations fill most operational gaps.
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 the schema fully documents all 14 parameters. The description summarizes the primary filter dimensions and candidate ID format but adds no semantic detail beyond a concise overview; per the high-coverage rule, 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 uses specific verbs ('Find', 'Retrieve') on a clear resource ('federal candidates') and names the main filter dimensions and the ID-lookup mode. It is unmistakably a candidate search, but it does not explicitly contrast itself with sibling tools like openfec_search_committees, so it stops just short of full sibling differentiation.
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 gives clear search contexts: filter by candidate attributes or fetch a single candidate by FEC ID, and it flags the financial-totals case. There are no exclusions or named alternatives, so the agent is not told when to prefer this over openfec_search_committees, but the intended invocation is explicit enough.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
openfec_search_committeesOpenfec Search CommitteesARead-onlyIdempotentInspect
Find political committees (campaign, PAC, Super PAC, party) by name, type, candidate affiliation, or state. Retrieve a specific committee by FEC ID. Committee IDs start with C followed by exactly eight digits (e.g., C00358796).
| Name | Required | Description | Default |
|---|---|---|---|
| page | No | Search-results page number (1-indexed). Defaults to 1 on the search path. | |
| cycle | No | Two-year election cycle (even year). | |
| party | No | Three-letter party code (e.g., DEM, REP). | |
| query | No | Full-text committee name search. | |
| state | No | Two-letter state code. | |
| per_page | No | Search results per page. Defaults to 20 on the search path. | |
| designation | No | Committee designation. A (authorized), B (lobbyist PAC), D (leadership PAC), J (joint fundraiser), P (principal campaign), U (unauthorized). | |
| candidate_id | No | Find committees linked to this candidate (authorized, leadership, joint fundraising). Get IDs from openfec_search_candidates results. | |
| committee_id | No | FEC committee ID: 'C' followed by exactly eight digits (e.g., C00358796). Get IDs from openfec_search_committees results. Returns a single committee with full detail. | |
| committee_type | No | Committee type code. Common: H (House), S (Senate), P (Presidential), O (Super PAC), N (PAC nonqualified), Q (PAC qualified), X (Party nonqualified), Y (Party qualified). | |
| treasurer_name | No | Full-text treasurer name search. |
Output Schema
| Name | Required | Description |
|---|---|---|
| error | No | Present when the call failed. Absent on success. |
| notice | No | Guidance when the response carries no committees: how to broaden a search that matched nothing, or which requested position ran out when committees did match. |
| committees | No | Committee result set; one record per match. |
| pagination | No | Page-based pagination metadata. |
| totalCount | No | Total matching committees before pagination. |
| search_criteria | No | Echo of the search filters this call applied, as the server parsed them, minus paging arguments. Always present — compare it against what you sent to confirm every filter was honoured. |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations already indicate a read-only, idempotent operation, and the description is consistent with that. It adds useful behavioral context by disclosing the C+8-digit ID format and single-committee retrieval, but it does not describe pagination, edge cases, or result limits. With annotations covering safety, this is adequate but not rich.
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?
Two concise, front-loaded sentences with no filler. The first sentence establishes the core search behavior and criteria, while the second adds the ID format detail that matters for exact lookups. Every clause 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?
With 11 parameters, no required fields, and a full output schema, the description plus structured metadata provides enough to invoke the tool correctly. It does not discuss pagination behavior or rate limits, but these are not essential for correct invocation and are partially covered by the page/per_page schema descriptions.
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 the schema already documents all parameters. The description adds little beyond restating search dimensions and the committee ID format, which the schema's committee_id field already explains in equivalent detail. This meets the baseline but does not compensate beyond it.
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 uses a specific verb and resource: 'Find political committees' and 'Retrieve a specific committee by FEC ID', with clear scope (campaign, PAC, Super PAC, party) and search attributes. It distinguishes itself from siblings by focusing on committees, but it never explicitly contrasts itself with openfec_search_candidates.
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 clearly states the intended use cases: search by name, type, candidate affiliation, or state, plus exact FEC ID lookup. It does not mention alternatives or when-not-to-use cases, so it stops short of full exclusion guidance, but the context is clear enough for an agent to select it for committee lookup.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
openfec_search_contributionsOpenfec Search ContributionsARead-onlyIdempotentInspect
Search itemized individual contributions (Schedule A) or get aggregate breakdowns by size, state, employer, or occupation. Use to answer "who is funding this committee?" Itemized mode requires a committee_id. Aggregate by_size/by_state can use candidate_id instead.
| Name | Required | Description | Default |
|---|---|---|---|
| mode | No | Query mode. "itemized" returns individual contribution records (keyset pagination). "by_size" aggregates by contribution size bucket. "by_state" aggregates by contributor state. "by_employer" aggregates by employer. "by_occupation" aggregates by occupation. | itemized |
| page | No | Page number (1-indexed) for aggregate modes. Explicit page is rejected in itemized mode, which paginates with cursor. Defaults to 1 for aggregates. | |
| sort | No | Sort field. A "-" prefix sorts descending: use "-contribution_receipt_amount" for the largest receipts first, since the ascending form leads with the most negative rows (refunds, reattributions, redesignations). Itemized only; OpenFEC sorts by "-contribution_receipt_date" when omitted. | |
| cycle | No | Two-year election cycle (e.g., 2024). Even years only. Defaults to current cycle for itemized mode. | |
| cursor | No | Opaque pagination cursor from a previous response of this tool. Itemized mode only (keyset pagination). Valid only for an otherwise-identical call — changing any other argument, including sort, rejects the cursor; omit it to start over. | |
| max_date | No | Latest contribution date (YYYY-MM-DD). Itemized only. | |
| min_date | No | Earliest contribution date (YYYY-MM-DD). Itemized only. | |
| per_page | No | Results per page. | |
| max_amount | No | Maximum contribution amount in dollars. Itemized only. | |
| min_amount | No | Minimum contribution amount in dollars. Itemized only. | |
| candidate_id | No | Candidate ID (e.g., P00003392). Get IDs from openfec_search_candidates results. Enables by_size and by_state aggregates without a committee_id. | |
| committee_id | No | Receiving committee ID (e.g., C00703975). Get IDs from openfec_search_committees results. | |
| is_individual | No | Only individual contributions (excludes committee-to-committee transfers). Itemized only. | |
| contributor_zip | No | ZIP code prefix (starts-with match). Itemized only. | |
| contributor_city | No | Contributor city. Itemized only. | |
| contributor_name | No | Full-text donor name search. Itemized only. | |
| contributor_state | No | Two-letter state code (e.g., CA). Itemized only. | |
| contributor_employer | No | Full-text employer search. Itemized only. | |
| contributor_occupation | No | Full-text occupation search. Itemized only. |
Output Schema
| Name | Required | Description |
|---|---|---|
| mode | No | Query mode as the server resolved it. "by_size" and "by_state" resolve to "by_size_candidate" / "by_state_candidate" when scoped by candidate_id — a different endpoint with different row shapes — so read this rather than assuming the mode you sent. |
| count | No | Total matching contributions (itemized mode). Check count_is_approximate before quoting it as a figure. |
| error | No | Present when the call failed. Absent on success. |
| notice | No | Guidance when the response needs context: how to broaden a search that matched nothing, which requested position ran out when contributions did match, or that the total is an estimate. |
| results | No | Contribution result set; itemized records or aggregate buckets depending on mode. |
| committee | No | The committee every row in this response belongs to, carried once instead of repeated in each row. Present only when the query was scoped to a single committee_id; otherwise each row keeps its own committee object. |
| pagination | No | Page-based pagination info (aggregate modes only). |
| totalCount | No | Total matching contributions or aggregate rows. |
| next_cursor | No | Pagination cursor for the next page of itemized results. Null when no more pages. |
| search_criteria | No | Echo of the search filters this call applied, as the server parsed them, minus paging arguments. Always present — compare it against what you sent to confirm every filter was honoured. |
| count_is_approximate | No | True when OpenFEC reports count as an estimate rather than a tally, which it does on its highest-volume queries. Absent means the count is a tally. |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The readOnlyHint and idempotentHint annotations already establish the safety profile, and the description adds mode constraints rather than new operational behavior such as pagination or response quirks. That is useful but modest, matching the baseline for a read-style tool with annotations 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?
Three sentences with no filler: mode list, use case, and mode-specific ID requirement are front-loaded and each sentence carries information. The natural-language breakdown names map directly to the mode enum values.
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 19-parameter tool the description plus fully documented schema and output schema cover the call correctly, including the critical committee_id requirement. It leaves by_employer/by_occupation funding requirements implicit ('by_size/by_state can use candidate_id instead' implies the others need committee_id), a minor gap.
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?
Input schema coverage is 100%, so the description does not need to enumerate parameters; the main text adds only a couple of high-level relationships (itemized requires committee_id; by_size/by_state can use candidate_id). This earns the baseline 3 but no higher because most parameter meaning is already 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?
Description opens with a specific action and resource: 'Search itemized individual contributions (Schedule A) or get aggregate breakdowns' and ties it to a concrete user intent ('who is funding this committee?'). This separates it from sibling tools that handle filings, disbursements, or expenditures.
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 gives clear context for when to use the tool and mode-specific selectors: itemized requires committee_id, while by_size/by_state can use candidate_id instead. It does not explicitly name exclusions or alternatives such as search_disbursements for spending questions, so it stops short of full routing guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
openfec_search_coordinated_expendituresOpenfec Search Coordinated ExpendituresARead-onlyIdempotentInspect
Search coordinated party expenditures (Schedule F) — spending a party committee makes on behalf of a candidate it supports, in coordination with that campaign. Distinct from independent expenditures (openfec_search_expenditures), which cannot be coordinated with the candidate, and from direct contributions: coordinated expenditures carry their own statutory limits and can run into tens of millions per party in a presidential cycle. Scope with a spending committee_id, a benefiting candidate_id, or a cycle; unscoped queries span all years.
| Name | Required | Description | Default |
|---|---|---|---|
| page | No | Page number (1-indexed). Read pagination.pages in the response to see how many pages exist. | |
| sort | No | Sort field. A "-" prefix sorts descending: use "-expenditure_amount" for the largest coordinated spending first, since the ascending form leads with the most negative rows (corrections and voided entries). OpenFEC sorts by "-expenditure_date" when omitted. | |
| cycle | No | Two-year election cycle (e.g., 2024). Even years only. Omitting it searches every cycle on record. | |
| max_date | No | Latest expenditure date (YYYY-MM-DD). | |
| min_date | No | Earliest expenditure date (YYYY-MM-DD). | |
| per_page | No | Results per page. | |
| max_amount | No | Maximum expenditure amount in dollars. | |
| min_amount | No | Minimum expenditure amount in dollars. | |
| payee_name | No | Full-text payee name search (the vendor the party paid). | |
| candidate_id | No | Benefiting candidate ID (e.g., P00003392). Get IDs from openfec_search_candidates results. | |
| committee_id | No | Spending party committee ID (e.g., C00003418). Get IDs from openfec_search_committees results — party committees carry committee_type X or Y. |
Output Schema
| Name | Required | Description |
|---|---|---|
| error | No | Present when the call failed. Absent on success. |
| notice | No | Guidance when the response carries no coordinated expenditures: how to broaden a search that matched nothing, or which requested position ran out when expenditures did match. |
| results | No | Coordinated expenditure result set; one record per itemized transaction. |
| committee | No | The committee every row in this response belongs to, carried once instead of repeated in each row. Present only when the query was scoped to a single committee_id; otherwise each row keeps its own committee object. |
| pagination | No | Page-based pagination metadata. |
| totalCount | No | Total matching coordinated expenditures before pagination. |
| search_criteria | No | Echo of the search filters this call applied, as the server parsed them, minus paging arguments. Always present — compare it against what you sent to confirm every filter was honoured. |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already establish readOnlyHint and idempotentHint, so the safety profile is covered. The description adds useful behavioral context beyond that: unscoped queries search all years, the data can reach tens of millions per party, and these expenditures carry their own statutory limits. This goes beyond a bare repeat of 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?
Three dense sentences with no filler: the first states purpose, the second distinguishes from related concepts while naming a sibling, and the third gives scoping behavior. It is front-loaded and every clause 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 an 11-parameter search tool with a full input schema, an output schema, and read-only/idempotent annotations, the description provides the missing conceptual and scoping context. Nothing critical is left unexplained for an agent to invoke the tool correctly.
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 the baseline is 3, but the description adds meaningful semantic grouping by identifying committee_id, candidate_id, and cycle as the primary scoping parameters. It also clarifies that omitting cycle means 'all years,' which supplements the individual parameter descriptions.
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 opens with a specific verb and resource ('Search coordinated party expenditures (Schedule F)') and immediately distinguishes the tool from independent expenditures and direct contributions. It names the sibling openfec_search_expenditures, so an agent can tell them apart without inspecting schemas.
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 what coordinated expenditures are not — independent expenditures and direct contributions — and names the sibling for independent expenditures. It also provides scoping guidance ('Scope with a spending committee_id, a benefiting candidate_id, or a cycle') and warns that unscoped queries span all years.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
openfec_search_disbursementsOpenfec Search DisbursementsARead-onlyIdempotentInspect
Search itemized committee spending (Schedule B) or get aggregate breakdowns by purpose or recipient. All modes require a committee_id. Use to answer "what is this committee spending money on?" or "who is receiving payments from this committee?"
| Name | Required | Description | Default |
|---|---|---|---|
| mode | No | Query mode. "itemized" returns individual disbursement records (keyset pagination). "by_purpose" aggregates by purpose category. "by_recipient" aggregates by recipient name. "by_recipient_id" aggregates by recipient committee ID (committee-to-committee transfers). | itemized |
| page | No | Page number (1-indexed) for aggregate modes. Explicit page is rejected in itemized mode, which paginates with cursor. Defaults to 1 for aggregates. | |
| sort | No | Sort field. A "-" prefix sorts descending: use "-disbursement_amount" for the biggest payments first, since the ascending form leads with the most negative rows (refunds and voided payments). Itemized only; OpenFEC sorts by "-disbursement_date" when omitted. | |
| cycle | No | Two-year election cycle (e.g., 2024). Even years only. Itemized mode defaults to the current cycle when omitted — Schedule B spans all history, and an all-history scan of an active committee times out upstream. Pass an explicit cycle to search an earlier period. | |
| cursor | No | Opaque pagination cursor from a previous response of this tool. Itemized mode only (keyset pagination). Valid only for an otherwise-identical call — changing any other argument, including sort, rejects the cursor; omit it to start over. | |
| max_date | No | Latest disbursement date (YYYY-MM-DD). Itemized only. | |
| min_date | No | Earliest disbursement date (YYYY-MM-DD). Itemized only. | |
| per_page | No | Results per page. | |
| max_amount | No | Maximum amount in dollars. Itemized only. | |
| min_amount | No | Minimum amount in dollars. Itemized only. | |
| committee_id | Yes | Spending committee ID (e.g., C00703975). Get IDs from openfec_search_committees results. Required for all modes. | |
| recipient_city | No | Recipient city. Itemized only. | |
| recipient_name | No | Full-text payee name search. Itemized only. | |
| recipient_state | No | Recipient state. Itemized only. | |
| recipient_committee_id | No | Recipient committee ID (for committee-to-committee transfers). Itemized only. | |
| disbursement_description | No | Full-text description search (e.g., "media buy", "consulting"). Itemized only. | |
| disbursement_purpose_category | No | Purpose category code. Itemized only. |
Output Schema
| Name | Required | Description |
|---|---|---|
| mode | No | Query mode as the server resolved it. Row shapes differ by mode — itemized rows are individual payments, aggregate rows are buckets with a total — so read this rather than inferring the shape from the fields present. |
| count | No | Total matching disbursements (itemized mode). Check count_is_approximate before quoting it as a figure. |
| error | No | Present when the call failed. Absent on success. |
| notice | No | Guidance when the response needs context: how to broaden a search that matched nothing, which requested position ran out when disbursements did match, or that the total is an estimate. |
| results | No | Disbursement result set; itemized records or aggregate buckets depending on mode. |
| committee | No | The committee every row in this response belongs to, carried once instead of repeated in each row. Present only when the query was scoped to a single committee_id; otherwise each row keeps its own committee object. |
| pagination | No | Page-based pagination info (aggregate modes only). |
| totalCount | No | Total matching disbursements or aggregate rows. |
| next_cursor | No | Pagination cursor for the next page of itemized results. Null when no more pages. |
| search_criteria | No | Echo of the search filters this call applied, as the server parsed them, minus paging arguments. Always present — compare it against what you sent to confirm every filter was honoured. |
| count_is_approximate | No | True when OpenFEC reports count as an estimate rather than a tally, which it does on its highest-volume queries. Absent means the count is a tally. |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and idempotentHint=true, so the safety profile is covered. The description adds context about the two behavior modes (itemized vs aggregate), but does not disclose other behavioral traits such as timeout behavior or pagination rules, which are left to the schema.
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?
Two sentences with no filler. The primary function is front-loaded, followed by the key requirement and illustrative use cases. 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 17-parameter tool with a rich schema and output schema, the description is adequately complete at the overview level. It successfully conveys the tool's scope and purpose, while the detailed parameter semantics are already captured in the input schema. A brief nod to the mode parameter would improve it, but nothing essential 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 the schema fully documents all 17 parameters. The tool description only mentions committee_id, adding no semantic detail beyond what the schema provides. Baseline 3 applies since the schema carries the burden.
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?
Description clearly states a specific verb ('Search') and resource ('itemized committee spending (Schedule B)'), and extends to aggregate breakdowns by purpose or recipient. It is specific enough that an agent can grasp the tool's function, though it does not explicitly name sibling tools like openfec_search_expenditures to differentiate them.
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 gives explicit use cases: answering 'what is this committee spending money on?' or 'who is receiving payments from this committee?' and states a hard prerequisite ('All modes require a committee_id'). It does not mention exclusions or alternative tools, but the contextual signals are clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
openfec_search_expendituresOpenfec Search ExpendituresARead-onlyIdempotentInspect
Search independent expenditures (Schedule E) — outside spending supporting or opposing federal candidates. Covers Super PACs, party committees, and other groups. Use itemized mode for individual expenditure records, or by_candidate for aggregated totals per candidate; by_candidate needs either a candidate_id or a full race scope (candidate_office alone for President, plus candidate_office_state for Senate, plus candidate_office_district as well for House).
| Name | Required | Description | Default |
|---|---|---|---|
| mode | No | Query mode. "itemized" returns individual expenditure records (keyset pagination). "by_candidate" returns aggregated totals per candidate by committee (page-based). | itemized |
| page | No | Page number (1-indexed) for by_candidate mode. Explicit page is rejected in itemized mode, which paginates with cursor. Defaults to 1 for by_candidate. | |
| sort | No | Sort field. A "-" prefix sorts descending: use "-expenditure_amount" for the largest outside spending first, since the ascending form leads with the most negative rows (corrections and voided entries). Itemized only; OpenFEC sorts by "-expenditure_date" when omitted. | |
| cycle | No | Two-year election cycle (e.g., 2024). Even years only. Itemized mode defaults to the current cycle when omitted — Schedule E spans all history and an unscoped scan times out upstream. Pass an explicit cycle to search an earlier period. | |
| cursor | No | Opaque pagination cursor from a previous response of this tool. Itemized mode only (keyset pagination). Valid only for an otherwise-identical call — changing any other argument, including sort, rejects the cursor; omit it to start over. | |
| max_date | No | Latest expenditure date (YYYY-MM-DD). Itemized only. | |
| min_date | No | Earliest expenditure date (YYYY-MM-DD). Itemized only. | |
| per_page | No | Results per page. | |
| is_notice | No | Only 24/48-hour notice filings (near-election spending). Itemized only. | |
| max_amount | No | Maximum expenditure amount in dollars. Itemized only. | |
| min_amount | No | Minimum expenditure amount in dollars. Itemized only. | |
| payee_name | No | Full-text payee name search. Itemized only. | |
| most_recent | No | Only the most recent version of amended filings. Itemized only — by_candidate rejects it. Defaults to true in itemized mode when omitted; pass false to see superseded versions of amended filings. | |
| candidate_id | No | Targeted candidate ID (e.g., P00003392). Get IDs from openfec_search_candidates results. | |
| committee_id | No | Spending committee ID (e.g., C00703975). Get IDs from openfec_search_committees results. | |
| support_oppose | No | S = support, O = oppose. Filter by whether the expenditure supports or opposes the candidate. | |
| candidate_party | No | Three-letter party code of the targeted candidate (e.g., DEM, REP). Itemized only — by_candidate rejects it, since the aggregate endpoint has no party filter. | |
| candidate_office | No | Office of the targeted candidate: H=House, S=Senate, P=President. In by_candidate mode this scopes a whole race: P stands alone, S also needs candidate_office_state, H also needs candidate_office_state and candidate_office_district. | |
| candidate_office_state | No | Two-letter state code of the targeted race. Required alongside candidate_office=H or candidate_office=S in by_candidate mode; leave it off for candidate_office=P, whose aggregate rows carry no state and match nothing when one is supplied. | |
| candidate_office_district | No | Two-digit House district of the targeted race (e.g., "09"). Required alongside candidate_office=H and candidate_office_state in by_candidate mode; Senate and presidential rows carry no district and match nothing when one is supplied. |
Output Schema
| Name | Required | Description |
|---|---|---|
| mode | No | Query mode as the server resolved it. Row shapes differ by mode — itemized rows are individual expenditures, by_candidate rows are per-candidate totals — so read this rather than inferring the shape from the fields present. |
| count | No | Total matching independent expenditures (itemized mode). Check count_is_approximate before quoting it as a figure. |
| error | No | Present when the call failed. Absent on success. |
| notice | No | Guidance when the response needs context: how to broaden a search that matched nothing, which requested position ran out when expenditures did match, or that the total is an estimate. |
| results | No | Expenditure result set; itemized records or per-candidate aggregates depending on mode. |
| committee | No | The committee every row in this response belongs to, carried once instead of repeated in each row. Present only when the query was scoped to a single committee_id; otherwise each row keeps its own committee object. |
| pagination | No | Page-based pagination info (by_candidate mode only). |
| totalCount | No | Total matching expenditures or per-candidate aggregates. |
| next_cursor | No | Pagination cursor for the next page of itemized results. Null when no more pages. |
| search_criteria | No | Echo of the search filters this call applied, as the server parsed them, minus paging arguments. Always present — compare it against what you sent to confirm every filter was honoured. |
| count_is_approximate | No | True when OpenFEC reports count as an estimate rather than a tally, which it does on its highest-volume queries. Absent means the count is a tally. |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and idempotentHint=true. The description adds behavioral value by explaining what each mode returns and by_candidate's candidate_id/race-scope requirements, which are not obvious from the tool name alone.
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 compact and front-loaded: first the purpose, then the mode choice, then the required by_candidate scope combinations. Every sentence adds useful information with no filler.
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 tool with 20 parameters, the description covers the most complex decision point—choosing between itemized and by_candidate—and the by_candidate race-scope rules. The output schema and parameter-level schema descriptions cover the remaining details, so the agent has what it needs to call the tool correctly.
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 the schema already documents all 20 parameters thoroughly. The narrative description adds mode-level framing but does not provide parameter-specific meaning beyond what the schema already explains.
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 names a specific resource ('independent expenditures (Schedule E)') with a clear verb ('Search') and adds scope ('outside spending supporting or opposing federal candidates'). It also covers what entities are included, which distinguishes it from sibling tools like coordinated expenditures.
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 gives clear guidance on the two modes ('Use itemized mode for individual expenditure records, or by_candidate for aggregated totals per candidate') and explains the key by_candidate scoping requirements. It does not explicitly name alternatives or exclusion conditions, but the independent-expenditure framing is clear enough for mode selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
openfec_search_filingsOpenfec Search FilingsARead-onlyIdempotentInspect
Search FEC filings and reports by committee, candidate, form type, or date range. Covers financial reports (F3/F3P/F3X), statements of candidacy (F2), organizational filings (F1), 24-hour IE notices (F24), and amendments.
| Name | Required | Description | Default |
|---|---|---|---|
| page | No | Page number (1-indexed). | |
| cycle | No | Two-year election cycle (even year). | |
| per_page | No | Results per page. | |
| form_type | No | FEC form type. Common: F3 (House/Senate quarterly), F3P (Presidential), F3X (PAC/party), F24 (24-hour IE notice), F1 (statement of organization), F2 (statement of candidacy), F5 (IE by persons). | |
| filer_name | No | Full-text filer name search. | |
| is_amended | No | Filter to original or amended filings only. | |
| most_recent | No | Only the most recent version (filters out superseded amendments). | |
| report_type | No | Report type code. Common: Q1/Q2/Q3 (quarterly), YE (year-end), M3-M12 (monthly), 12G/12P/30G (pre/post election). | |
| report_year | No | Filing year. | |
| candidate_id | No | Associated candidate ID (e.g., P00003392). Get IDs from openfec_search_candidates results. | |
| committee_id | No | Filing committee ID (e.g., C00358796). Get IDs from openfec_search_committees results. | |
| max_receipt_date | No | Latest FEC receipt date (YYYY-MM-DD). | |
| min_receipt_date | No | Earliest date FEC received the filing (YYYY-MM-DD). |
Output Schema
| Name | Required | Description |
|---|---|---|
| error | No | Present when the call failed. Absent on success. |
| notice | No | Guidance when the response needs context: how to broaden a search that matched nothing, which requested position ran out when filings did match, or that the total is an estimate. |
| results | No | Filing result set; one record per match. |
| pagination | No | Page-based pagination metadata. |
| totalCount | No | Total matching filings before pagination. |
| search_criteria | No | Echo of the search filters this call applied, as the server parsed them, minus paging arguments. Always present — compare it against what you sent to confirm every filter was honoured. |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and idempotentHint=true, so there is no safety contradiction. The description adds useful context about covered form types and amendments, but it does not disclose behavioral details such as pagination behavior or how the most_recent filter interacts with amended filings.
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 dense, front-loaded sentences with no filler. The first sentence states the action and resource; the second adds a useful inventory of covered form types. Every clause contributes value.
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 rich schema and output schema carry most of the parameter and return-value burden, while the description adds domain context about which FEC forms are covered. The main gap is lack of explicit routing guidance among sibling search tools, but nothing essential for invoking this tool correctly 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?
The schema provides 100% description coverage across all 13 parameters, including defaults, common form types, and report codes. The description only restates high-level filter dimensions already present in the schema and adds no new syntax, format, or parameter-specific guidance, so it stays at the baseline.
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 opens with a specific verb ('Search') and a specific resource ('FEC filings and reports'), then enumerates the filter dimensions and form types covered. This clearly distinguishes it from sibling tools like openfec_search_contributions or openfec_search_candidates without requiring schema inspection.
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 clearly implies this tool is for finding FEC filings and reports by committee, candidate, form type, or date range, but it never explicitly says when to prefer this over the sibling search tools or when not to use it. Cross-references to openfec_search_candidates and openfec_search_committees exist only in parameter descriptions, not in the main description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
openfec_search_legalOpenfec Search LegalARead-onlyIdempotentInspect
Search FEC legal documents: advisory opinions, enforcement cases (MURs), alternative dispute resolutions, and administrative fines.
| Name | Required | Description | Default |
|---|---|---|---|
| type | No | Document type filter. Omit to search all types. admin_fines is slow without a query or respondent filter. | |
| query | No | Full-text search across legal documents. | |
| from_hit | No | Offset for pagination (0-indexed), counted within each document type rather than across them. Default 0. The search index serves a 10,000-result window, so from_hit plus hits_returned must be 10,000 or less — the ceiling here assumes hits_returned of 1. | |
| max_date | No | Latest date (YYYY-MM-DD) for the date_kind selected. Requires type and date_kind. | |
| min_date | No | Earliest date (YYYY-MM-DD) for the date_kind selected. Requires type and date_kind. | |
| ao_number | No | Specific advisory opinion number (e.g. "2024-01"). | |
| date_kind | No | Which date min_date/max_date bound. Each document type records its own dates, so this must be one the chosen type has: type=advisory_opinions → issue_date (opinion issued), request_date (request received), document_date; type=murs or adrs → open_date (case opened), close_date (case closed), document_date; type=admin_fines → rtb_date (reason-to-believe finding), fd_date (final determination). type=statutes cannot be date-filtered. Required whenever min_date or max_date is given, together with type. | |
| respondent | No | Respondent name (enforcement cases). | |
| case_number | No | Specific MUR or ADR case number. | |
| hits_returned | No | Results per page, applied per document type. Default 20, max 200. Bounded together with from_hit by the 10,000-result window. | |
| max_penalty_amount | No | Maximum penalty amount in dollars. Filters enforcement cases (murs, adrs) only — other document types are returned unfiltered by it. | |
| min_penalty_amount | No | Minimum penalty amount in dollars. Filters enforcement cases (murs, adrs) only — other document types are returned unfiltered by it. | |
| statutory_citation | No | U.S.C. citation (e.g. "52 U.S.C. 30106"). | |
| regulatory_citation | No | CFR citation (e.g. "11 CFR 112.4"). |
Output Schema
| Name | Required | Description |
|---|---|---|
| error | No | Present when the call failed. Absent on success. |
| notice | No | Guidance when the response carries no legal documents: how to broaden a search that matched nothing, or that from_hit ran past the end when documents did match. |
| results | No | Legal document result set spanning advisory opinions, MURs, ADRs, admin fines, and statutes. |
| totalCount | No | Total matching legal documents across all types. |
| total_count | No | Total matching documents across all types. |
| retrievalHint | No | How to recover the material trimmed out of these results. Present whenever any result was returned, because every result is trimmed. |
| search_criteria | No | Echo of the search filters this call applied, as the server parsed them, minus paging arguments. Always present — compare it against what you sent to confirm every filter was honoured. |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations declare readOnlyHint and idempotentHint, so the agent knows this is a safe read operation. The description doesn't contradict these. The description adds context about the scope of the search (covering specific document types) and notes that admin_fines is slow without a query or respondent filter (within the schema, but still beyond the annotations). It could have mentioned the 10,000-result window, but that is in the schema. Given the strong annotations, the description does add value by clarifying what it searches, and it doesn't need to reiterate safety.
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 a single, concise sentence that fully captures the tool's purpose. It is front-loaded with the core function ('Search FEC legal documents') and immediately lists the types, making it scannable for an agent. No wasted words. It could have been longer, but it is appropriately minimal for a search tool with extensive schema documentation.
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 14 parameters, 2 enums, and the presence of an output schema, the description is complete enough. The schema covers parameter semantics, defaults, and constraints. The description clarifies the tool's scope and the existing annotations cover safety. The agent has all necessary information to call the tool correctly, including pagination limits and date-kind rules from the schema. There are no significant gaps.
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 the schema already thoroughly documents all 14 parameters, including enums, defaults, and constraints. The description itself does not add much beyond the schema, but it doesn't need to because the schema is rich. The description's mention of document types is already captured in the type enum. Therefore, baseline 3 is appropriate; the schema does the heavy lifting.
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 states a specific verb ('Search') and a clear resource ('FEC legal documents'), and enumerates the document types covered (advisory opinions, MURs, ADRs, administrative fines). This distinguishes it from sibling tools like openfec_get_legal_document, which is about retrieving a specific document, not searching across types. The description is precise and immediately tells the agent what this tool does.
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 clearly establishes the context: searching legal documents. It implies this is the tool to use when you need to find legal documents by various filters. It does not explicitly state when not to use it or mention alternatives, but the sibling list includes openfec_get_legal_document, which is clearly a different operation. The schema's parameter descriptions add usage guidance (e.g., date_kind requirements), but the main description could be a bit more explicit about when to choose this over other search tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
11 tool updates
- Changed
openfec_get_committee_totals2 fields changed- changed
Output schema / properties / notice / descriptionPrevious value: -"Guidance when no totals matched — echoes filters and suggests how to broaden."New value: +"Guidance when the response carries no totals: how to broaden a search that matched nothing, or which requested position ran out when totals did match." - added
Output schema / properties / pagination / properties / count_is_approximateAdded value: +{ + "description": "True when OpenFEC reports this count as an estimate rather than a tally, which it does on its highest-volume datasets. Absent means the count is a tally. An estimated count — and the pages derived from it — can be off by a wide margin; treat it as an order of magnitude, not a figure to quote.", + "type": "boolean" +}
- Changed
openfec_lookup_calendar2 fields changed- changed
Output schema / properties / notice / descriptionPrevious value: -"Guidance when no calendar entries matched — echoes filters and suggests how to broaden."New value: +"Guidance when the response carries no calendar entries: how to broaden a search that matched nothing, or which requested position ran out when entries did match." - added
Output schema / properties / pagination / properties / count_is_approximateAdded value: +{ + "description": "True when OpenFEC reports this count as an estimate rather than a tally, which it does on its highest-volume datasets. Absent means the count is a tally. An estimated count — and the pages derived from it — can be off by a wide margin; treat it as an order of magnitude, not a figure to quote.", + "type": "boolean" +}
- Changed
openfec_lookup_elections2 fields changed- changed
Output schema / properties / notice / descriptionPrevious value: -"Guidance when no election results matched — echoes filters and suggests how to broaden."New value: +"Guidance when the response carries no election results: how to broaden a search that matched nothing, or which requested position ran out when results did match." - added
Output schema / properties / pagination / properties / count_is_approximateAdded value: +{ + "description": "True when OpenFEC reports this count as an estimate rather than a tally, which it does on its highest-volume datasets. Absent means the count is a tally. An estimated count — and the pages derived from it — can be off by a wide margin; treat it as an order of magnitude, not a figure to quote.", + "type": "boolean" +}
- Changed
openfec_search_candidates2 fields changed- changed
Output schema / properties / notice / descriptionPrevious value: -"Guidance when no candidates matched — echoes filters and suggests how to broaden."New value: +"Guidance when the response carries no candidates: how to broaden a search that matched nothing, or which requested position ran out when candidates did match." - added
Output schema / properties / pagination / properties / count_is_approximateAdded value: +{ + "description": "True when OpenFEC reports this count as an estimate rather than a tally, which it does on its highest-volume datasets. Absent means the count is a tally. An estimated count — and the pages derived from it — can be off by a wide margin; treat it as an order of magnitude, not a figure to quote.", + "type": "boolean" +}
- Changed
openfec_search_committees2 fields changed- changed
Output schema / properties / notice / descriptionPrevious value: -"Guidance when no committees matched — echoes filters and suggests how to broaden."New value: +"Guidance when the response carries no committees: how to broaden a search that matched nothing, or which requested position ran out when committees did match." - added
Output schema / properties / pagination / properties / count_is_approximateAdded value: +{ + "description": "True when OpenFEC reports this count as an estimate rather than a tally, which it does on its highest-volume datasets. Absent means the count is a tally. An estimated count — and the pages derived from it — can be off by a wide margin; treat it as an order of magnitude, not a figure to quote.", + "type": "boolean" +}
- Changed
openfec_search_contributions4 fields changed- changed
Output schema / properties / count / descriptionPrevious value: -"Total result count (may be approximate for itemized)."New value: +"Total matching contributions (itemized mode). Check count_is_approximate before quoting it as a figure." - added
Output schema / properties / count_is_approximateAdded value: +{ + "description": "True when OpenFEC reports count as an estimate rather than a tally, which it does on its highest-volume queries. Absent means the count is a tally.", + "type": "boolean" +} - changed
Output schema / properties / notice / descriptionPrevious value: -"Guidance when no contributions matched — echoes filters and suggests how to broaden."New value: +"Guidance when the response needs context: how to broaden a search that matched nothing, which requested position ran out when contributions did match, or that the total is an estimate." - added
Output schema / properties / pagination / properties / count_is_approximateAdded value: +{ + "description": "True when OpenFEC reports this count as an estimate rather than a tally, which it does on its highest-volume datasets. Absent means the count is a tally. An estimated count — and the pages derived from it — can be off by a wide margin; treat it as an order of magnitude, not a figure to quote.", + "type": "boolean" +}
- Changed
openfec_search_coordinated_expenditures2 fields changed- changed
Output schema / properties / notice / descriptionPrevious value: -"Guidance when no coordinated expenditures matched — echoes filters and suggests how to broaden."New value: +"Guidance when the response carries no coordinated expenditures: how to broaden a search that matched nothing, or which requested position ran out when expenditures did match." - added
Output schema / properties / pagination / properties / count_is_approximateAdded value: +{ + "description": "True when OpenFEC reports this count as an estimate rather than a tally, which it does on its highest-volume datasets. Absent means the count is a tally. An estimated count — and the pages derived from it — can be off by a wide margin; treat it as an order of magnitude, not a figure to quote.", + "type": "boolean" +}
- Changed
openfec_search_disbursements4 fields changed- changed
Output schema / properties / count / descriptionPrevious value: -"Total result count (may be approximate for itemized)."New value: +"Total matching disbursements (itemized mode). Check count_is_approximate before quoting it as a figure." - added
Output schema / properties / count_is_approximateAdded value: +{ + "description": "True when OpenFEC reports count as an estimate rather than a tally, which it does on its highest-volume queries. Absent means the count is a tally.", + "type": "boolean" +} - changed
Output schema / properties / notice / descriptionPrevious value: -"Guidance when no disbursements matched — echoes filters and suggests how to broaden."New value: +"Guidance when the response needs context: how to broaden a search that matched nothing, which requested position ran out when disbursements did match, or that the total is an estimate." - added
Output schema / properties / pagination / properties / count_is_approximateAdded value: +{ + "description": "True when OpenFEC reports this count as an estimate rather than a tally, which it does on its highest-volume datasets. Absent means the count is a tally. An estimated count — and the pages derived from it — can be off by a wide margin; treat it as an order of magnitude, not a figure to quote.", + "type": "boolean" +}
- Changed
openfec_search_expenditures4 fields changed- changed
Output schema / properties / count / descriptionPrevious value: -"Total result count (may be approximate for itemized)."New value: +"Total matching independent expenditures (itemized mode). Check count_is_approximate before quoting it as a figure." - added
Output schema / properties / count_is_approximateAdded value: +{ + "description": "True when OpenFEC reports count as an estimate rather than a tally, which it does on its highest-volume queries. Absent means the count is a tally.", + "type": "boolean" +} - changed
Output schema / properties / notice / descriptionPrevious value: -"Guidance when no expenditures matched — echoes filters and suggests how to broaden."New value: +"Guidance when the response needs context: how to broaden a search that matched nothing, which requested position ran out when expenditures did match, or that the total is an estimate." - added
Output schema / properties / pagination / properties / count_is_approximateAdded value: +{ + "description": "True when OpenFEC reports this count as an estimate rather than a tally, which it does on its highest-volume datasets. Absent means the count is a tally. An estimated count — and the pages derived from it — can be off by a wide margin; treat it as an order of magnitude, not a figure to quote.", + "type": "boolean" +}
- Changed
openfec_search_filings2 fields changed- changed
Output schema / properties / notice / descriptionPrevious value: -"Guidance when no filings matched — echoes filters and suggests how to broaden."New value: +"Guidance when the response needs context: how to broaden a search that matched nothing, which requested position ran out when filings did match, or that the total is an estimate." - added
Output schema / properties / pagination / properties / count_is_approximateAdded value: +{ + "description": "True when OpenFEC reports this count as an estimate rather than a tally, which it does on its highest-volume datasets. Absent means the count is a tally. An estimated count — and the pages derived from it — can be off by a wide margin; treat it as an order of magnitude, not a figure to quote.", + "type": "boolean" +}
- Changed
openfec_search_legal6 fields changed- changed
Input schema / properties / from_hit / descriptionPrevious value: -"Offset for pagination (0-indexed). Default 0."New value: +"Offset for pagination (0-indexed), counted within each document type rather than across them. Default 0. The search index serves a 10,000-result window, so from_hit plus hits_returned must be 10,000 or less — the ceiling here assumes hits_returned of 1." - changed
Input schema / properties / from_hit / maximumPrevious value: -9007199254740991New value: +9999 - changed
Input schema / properties / hits_returned / descriptionPrevious value: -"Results per page. Default 20, max 200."New value: +"Results per page, applied per document type. Default 20, max 200. Bounded together with from_hit by the 10,000-result window." - changed
Output schema / properties / error / properties / data / properties / reason / descriptionPrevious value: -"Machine-readable failure mode. Declared by this tool: `missing_filter`: Called without any scoping filter at all. `date_filter_incomplete`: min_date or max_date given without both a type and a date_kind, or a date_kind given with neither bound. `date_kind_not_valid_for_type`: The requested date_kind is not a date this document type records. Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `missing_filter`: Called without any scoping filter at all. `date_filter_incomplete`: min_date or max_date given without both a type and a date_kind, or a date_kind given with neither bound. `date_kind_not_valid_for_type`: The requested date_kind is not a date this document type records. `legal_window_exceeded`: from_hit plus hits_returned exceeds the 10,000-result window the search index serves. Other values are possible when a failure originates below the handler." - changed
Output schema / properties / error / properties / data / properties / reason / examplesPrevious value: -[ - "missing_filter", - "date_filter_incomplete", - "date_kind_not_valid_for_type" -]New value: +[ + "missing_filter", + "date_filter_incomplete", + "date_kind_not_valid_for_type", + "legal_window_exceeded" +] - changed
Output schema / properties / notice / descriptionPrevious value: -"Guidance when no legal documents matched — echoes filters and suggests how to broaden."New value: +"Guidance when the response carries no legal documents: how to broaden a search that matched nothing, or that from_hit ran past the end when documents did match."
10 tool updates
- Changed
openfec_get_committee_totals1 field changed- changed
Output schema / properties / error / properties / data / properties / reason / descriptionPrevious value: -"Machine-readable failure mode. Declared by this tool: `committee_id_required_for_single_mode`: Mode single invoked without a committee_id `entity_type_required_for_group_mode`: Mode by_entity_type invoked without an entity_type `inputs_not_applicable_to_mode`: A grouped-search filter (entity_type, committee_state, committee_type, committee_designation, organization_type, or a receipts/disbursements bound) was supplied alongside mode single, which cannot apply it `committee_totals_not_found`: Single-committee lookup matched no totals row — the committee_id does not exist, it filed nothing in the requested cycle, or it has never filed a financial report at all Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `committee_id_required_for_single_mode`: Mode single invoked without a committee_id. `entity_type_required_for_group_mode`: Mode by_entity_type invoked without an entity_type. `inputs_not_applicable_to_mode`: A grouped-search filter (entity_type, committee_state, committee_type, committee_designation, organization_type, or a receipts/disbursements bound) was supplied alongside mode single, which cannot apply it. `committee_totals_not_found`: Single-committee lookup matched no totals row — the committee_id does not exist, it filed nothing in the requested cycle, or it has never filed a financial report at all. Other values are possible when a failure originates below the handler."
- Changed
openfec_get_legal_document1 field changed- changed
Output schema / properties / error / properties / data / properties / reason / descriptionPrevious value: -"Machine-readable failure mode. Declared by this tool: `legal_document_not_found`: No legal document exists at the requested doc_type and no Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `legal_document_not_found`: No legal document exists at the requested doc_type and document number. Other values are possible when a failure originates below the handler."
- Changed
openfec_lookup_calendar1 field changed- changed
Output schema / properties / error / properties / data / properties / reason / descriptionPrevious value: -"Machine-readable failure mode. Declared by this tool: `inputs_not_applicable_to_mode`: A filter belonging to a different calendar mode was supplied, which the chosen mode cannot apply Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `inputs_not_applicable_to_mode`: A filter belonging to a different calendar mode was supplied, which the chosen mode cannot apply. Other values are possible when a failure originates below the handler."
- Changed
openfec_lookup_elections1 field changed- changed
Output schema / properties / error / properties / data / properties / reason / descriptionPrevious value: -"Machine-readable failure mode. Declared by this tool: `cycle_must_be_even`: Cycle is an odd year `missing_state_for_office`: Senate or House office without a state and without a zip `missing_district_for_house`: House office without a district number and without a zip `summary_does_not_support_zip`: Summary mode invoked with a zip parameter `inputs_not_applicable_to_mode`: The resolved elections endpoint does not accept one or more explicitly supplied inputs Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `cycle_must_be_even`: Cycle is an odd year. `missing_state_for_office`: Senate or House office without a state and without a zip. `missing_district_for_house`: House office without a district number and without a zip. `summary_does_not_support_zip`: Summary mode invoked with a zip parameter. `inputs_not_applicable_to_mode`: The resolved elections endpoint does not accept one or more explicitly supplied inputs. Other values are possible when a failure originates below the handler."
- Changed
openfec_search_candidates1 field changed- changed
Output schema / properties / error / properties / data / properties / reason / descriptionPrevious value: -"Machine-readable failure mode. Declared by this tool: `candidate_not_found`: Single-candidate lookup by candidate_id returned no record `inputs_not_applicable_to_id_lookup`: A direct candidate_id lookup includes search-only inputs, or totals-only scope while include_totals is false Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `candidate_not_found`: Single-candidate lookup by candidate_id returned no record. `inputs_not_applicable_to_id_lookup`: A direct candidate_id lookup includes search-only inputs, or totals-only scope while include_totals is false. Other values are possible when a failure originates below the handler."
- Changed
openfec_search_committees1 field changed- changed
Output schema / properties / error / properties / data / properties / reason / descriptionPrevious value: -"Machine-readable failure mode. Declared by this tool: `committee_not_found`: Single-committee lookup by committee_id returned no record `inputs_not_applicable_to_id_lookup`: A direct committee_id lookup includes inputs that only the committee search endpoint supports Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `committee_not_found`: Single-committee lookup by committee_id returned no record. `inputs_not_applicable_to_id_lookup`: A direct committee_id lookup includes inputs that only the committee search endpoint supports. Other values are possible when a failure originates below the handler."
- Changed
openfec_search_contributions3 fields changed- changed
Output schema / properties / error / properties / data / properties / reason / descriptionPrevious value: -"Machine-readable failure mode. Declared by this tool: `itemized_requires_committee_id`: Itemized mode invoked without a committee_id `aggregate_requires_committee_id`: by_employer or by_occupation aggregate without a committee_id `itemized_only_filters_in_aggregate_mode`: An itemized-only filter was supplied alongside an aggregate mode, which cannot apply it `inputs_not_applicable_to_mode`: The resolved Schedule A endpoint does not accept one or more explicitly supplied inputs Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `itemized_requires_committee_id`: Itemized mode invoked without a committee_id. `aggregate_requires_committee_id`: by_employer or by_occupation aggregate without a committee_id. `itemized_only_filters_in_aggregate_mode`: An itemized-only filter was supplied alongside an aggregate mode, which cannot apply it. `inputs_not_applicable_to_mode`: The resolved Schedule A endpoint does not accept one or more explicitly supplied inputs. Other values are possible when a failure originates below the handler." - removed
Output schema / properties / next_cursor / anyOfRemoved value: -[ - { - "type": "string" - }, - { - "type": "null" - } -] - added
Output schema / properties / next_cursor / typeAdded value: +[ + "string", + "null" +]
- Changed
openfec_search_disbursements3 fields changed- changed
Output schema / properties / error / properties / data / properties / reason / descriptionPrevious value: -"Machine-readable failure mode. Declared by this tool: `itemized_only_filters_in_aggregate_mode`: An itemized-only filter was supplied alongside an aggregate mode, which cannot apply it `inputs_not_applicable_to_mode`: Itemized mode receives an explicit page number that its keyset endpoint cannot apply Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `itemized_only_filters_in_aggregate_mode`: An itemized-only filter was supplied alongside an aggregate mode, which cannot apply it. `inputs_not_applicable_to_mode`: Itemized mode receives an explicit page number that its keyset endpoint cannot apply. Other values are possible when a failure originates below the handler." - removed
Output schema / properties / next_cursor / anyOfRemoved value: -[ - { - "type": "string" - }, - { - "type": "null" - } -] - added
Output schema / properties / next_cursor / typeAdded value: +[ + "string", + "null" +]
- Changed
openfec_search_expenditures3 fields changed- changed
Output schema / properties / error / properties / data / properties / reason / descriptionPrevious value: -"Machine-readable failure mode. Declared by this tool: `by_candidate_requires_scope`: by_candidate mode invoked without a candidate_id and without a full race scope `itemized_only_filters_in_aggregate_mode`: An itemized-only filter (payee_name, candidate_party, a date or amount bound, is_notice, most_recent, sort, cursor) was supplied alongside mode by_candidate, which cannot apply it `inputs_not_applicable_to_mode`: Itemized mode receives an explicit page number that its keyset endpoint cannot apply Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `by_candidate_requires_scope`: by_candidate mode invoked without a candidate_id and without a full race scope. `itemized_only_filters_in_aggregate_mode`: An itemized-only filter (payee_name, candidate_party, a date or amount bound, is_notice, most_recent, sort, cursor) was supplied alongside mode by_candidate, which cannot apply it. `inputs_not_applicable_to_mode`: Itemized mode receives an explicit page number that its keyset endpoint cannot apply. Other values are possible when a failure originates below the handler." - removed
Output schema / properties / next_cursor / anyOfRemoved value: -[ - { - "type": "string" - }, - { - "type": "null" - } -] - added
Output schema / properties / next_cursor / typeAdded value: +[ + "string", + "null" +]
- Changed
openfec_search_legal1 field changed- changed
Output schema / properties / error / properties / data / properties / reason / descriptionPrevious value: -"Machine-readable failure mode. Declared by this tool: `missing_filter`: Called without any scoping filter at all `date_filter_incomplete`: min_date or max_date given without both a type and a date_kind, or a date_kind given with neither bound `date_kind_not_valid_for_type`: The requested date_kind is not a date this document type records Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `missing_filter`: Called without any scoping filter at all. `date_filter_incomplete`: min_date or max_date given without both a type and a date_kind, or a date_kind given with neither bound. `date_kind_not_valid_for_type`: The requested date_kind is not a date this document type records. Other values are possible when a failure originates below the handler."
6 tool updates
- Changed
openfec_lookup_elections5 fields changed- removed
Input schema / properties / page / defaultRemoved value: -1 - changed
Input schema / properties / page / descriptionPrevious value: -"Page number (1-indexed). Search mode only — summary mode returns a single aggregate row. Read pagination.pages in the response to see how many pages exist."New value: +"Page number (1-indexed). Search mode only; explicit page is rejected in summary mode. Defaults to 1 for search." - removed
Input schema / properties / per_page / defaultRemoved value: -20 - changed
Input schema / properties / per_page / descriptionPrevious value: -"Results per page. Search mode only."New value: +"Results per page. Search mode only; defaults to 20." - changed
Output schema / properties / error / properties / data / properties / reason / descriptionPrevious value: -"Machine-readable failure mode. Declared by this tool: `cycle_must_be_even`: Cycle is an odd year `missing_state_for_office`: Senate or House office without a state and without a zip `missing_district_for_house`: House office without a district number and without a zip `summary_does_not_support_zip`: Summary mode invoked with a zip parameter `inputs_not_applicable_to_mode`: election_full supplied alongside zip — a ZIP-scoped search runs an endpoint that has no such parameter Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `cycle_must_be_even`: Cycle is an odd year `missing_state_for_office`: Senate or House office without a state and without a zip `missing_district_for_house`: House office without a district number and without a zip `summary_does_not_support_zip`: Summary mode invoked with a zip parameter `inputs_not_applicable_to_mode`: The resolved elections endpoint does not accept one or more explicitly supplied inputs Other values are possible when a failure originates below the handler."
- Changed
openfec_search_candidates7 fields changed- changed
Input schema / properties / candidate_id / descriptionPrevious value: -"FEC candidate ID (e.g., P00003392, H2CO07170). Get IDs from openfec_search_candidates results. When provided, returns a single candidate with full detail."New value: +"FEC candidate ID: H, S, or P followed by exactly eight letters or digits (e.g., P00003392, H2CO07170). Get IDs from openfec_search_candidates results. When provided, returns a single candidate with full detail." - removed
Input schema / properties / page / defaultRemoved value: -1 - changed
Input schema / properties / page / descriptionPrevious value: -"Page number (1-indexed)."New value: +"Search-results page number (1-indexed). Defaults to 1 on the search path." - removed
Input schema / properties / per_page / defaultRemoved value: -20 - changed
Input schema / properties / per_page / descriptionPrevious value: -"Results per page."New value: +"Search results per page. Defaults to 20 on the search path." - changed
Output schema / properties / error / properties / data / properties / reason / descriptionPrevious value: -"Machine-readable failure mode. Declared by this tool: `candidate_not_found`: Single-candidate lookup by candidate_id returned no record Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `candidate_not_found`: Single-candidate lookup by candidate_id returned no record `inputs_not_applicable_to_id_lookup`: A direct candidate_id lookup includes search-only inputs, or totals-only scope while include_totals is false Other values are possible when a failure originates below the handler." - changed
Output schema / properties / error / properties / data / properties / reason / examplesPrevious value: -[ - "candidate_not_found" -]New value: +[ + "candidate_not_found", + "inputs_not_applicable_to_id_lookup" +]
- Changed
openfec_search_committees7 fields changed- changed
Input schema / properties / committee_id / descriptionPrevious value: -"FEC committee ID (e.g., C00358796). Get IDs from openfec_search_committees results. Starts with 'C' followed by digits. Returns a single committee with full detail."New value: +"FEC committee ID: 'C' followed by exactly eight digits (e.g., C00358796). Get IDs from openfec_search_committees results. Returns a single committee with full detail." - removed
Input schema / properties / page / defaultRemoved value: -1 - changed
Input schema / properties / page / descriptionPrevious value: -"Page number (1-indexed)."New value: +"Search-results page number (1-indexed). Defaults to 1 on the search path." - removed
Input schema / properties / per_page / defaultRemoved value: -20 - changed
Input schema / properties / per_page / descriptionPrevious value: -"Results per page."New value: +"Search results per page. Defaults to 20 on the search path." - changed
Output schema / properties / error / properties / data / properties / reason / descriptionPrevious value: -"Machine-readable failure mode. Declared by this tool: `committee_not_found`: Single-committee lookup by committee_id returned no record Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `committee_not_found`: Single-committee lookup by committee_id returned no record `inputs_not_applicable_to_id_lookup`: A direct committee_id lookup includes inputs that only the committee search endpoint supports Other values are possible when a failure originates below the handler." - changed
Output schema / properties / error / properties / data / properties / reason / examplesPrevious value: -[ - "committee_not_found" -]New value: +[ + "committee_not_found", + "inputs_not_applicable_to_id_lookup" +]
- Changed
openfec_search_contributions4 fields changed- removed
Input schema / properties / page / defaultRemoved value: -1 - changed
Input schema / properties / page / descriptionPrevious value: -"Page number (1-indexed) for the aggregate modes. Ignored in itemized mode, which paginates with cursor. Read pagination.pages in the response to see how many pages exist."New value: +"Page number (1-indexed) for aggregate modes. Explicit page is rejected in itemized mode, which paginates with cursor. Defaults to 1 for aggregates." - changed
Output schema / properties / error / properties / data / properties / reason / descriptionPrevious value: -"Machine-readable failure mode. Declared by this tool: `itemized_requires_committee_id`: Itemized mode invoked without a committee_id `aggregate_requires_committee_id`: by_employer or by_occupation aggregate without a committee_id `itemized_only_filters_in_aggregate_mode`: An itemized-only filter was supplied alongside an aggregate mode, which cannot apply it Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `itemized_requires_committee_id`: Itemized mode invoked without a committee_id `aggregate_requires_committee_id`: by_employer or by_occupation aggregate without a committee_id `itemized_only_filters_in_aggregate_mode`: An itemized-only filter was supplied alongside an aggregate mode, which cannot apply it `inputs_not_applicable_to_mode`: The resolved Schedule A endpoint does not accept one or more explicitly supplied inputs Other values are possible when a failure originates below the handler." - changed
Output schema / properties / error / properties / data / properties / reason / examplesPrevious value: -[ - "itemized_requires_committee_id", - "aggregate_requires_committee_id", - "itemized_only_filters_in_aggregate_mode" -]New value: +[ + "itemized_requires_committee_id", + "aggregate_requires_committee_id", + "itemized_only_filters_in_aggregate_mode", + "inputs_not_applicable_to_mode" +]
- Changed
openfec_search_disbursements4 fields changed- removed
Input schema / properties / page / defaultRemoved value: -1 - changed
Input schema / properties / page / descriptionPrevious value: -"Page number (1-indexed) for the aggregate modes. Ignored in itemized mode, which paginates with cursor. Read pagination.pages in the response to see how many pages exist."New value: +"Page number (1-indexed) for aggregate modes. Explicit page is rejected in itemized mode, which paginates with cursor. Defaults to 1 for aggregates." - changed
Output schema / properties / error / properties / data / properties / reason / descriptionPrevious value: -"Machine-readable failure mode. Declared by this tool: `itemized_only_filters_in_aggregate_mode`: An itemized-only filter was supplied alongside an aggregate mode, which cannot apply it Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `itemized_only_filters_in_aggregate_mode`: An itemized-only filter was supplied alongside an aggregate mode, which cannot apply it `inputs_not_applicable_to_mode`: Itemized mode receives an explicit page number that its keyset endpoint cannot apply Other values are possible when a failure originates below the handler." - changed
Output schema / properties / error / properties / data / properties / reason / examplesPrevious value: -[ - "itemized_only_filters_in_aggregate_mode" -]New value: +[ + "itemized_only_filters_in_aggregate_mode", + "inputs_not_applicable_to_mode" +]
- Changed
openfec_search_expenditures4 fields changed- removed
Input schema / properties / page / defaultRemoved value: -1 - changed
Input schema / properties / page / descriptionPrevious value: -"Page number (1-indexed) for by_candidate mode. Ignored in itemized mode, which paginates with cursor. Read pagination.pages in the response to see how many pages exist."New value: +"Page number (1-indexed) for by_candidate mode. Explicit page is rejected in itemized mode, which paginates with cursor. Defaults to 1 for by_candidate." - changed
Output schema / properties / error / properties / data / properties / reason / descriptionPrevious value: -"Machine-readable failure mode. Declared by this tool: `by_candidate_requires_scope`: by_candidate mode invoked without a candidate_id and without a full race scope `itemized_only_filters_in_aggregate_mode`: An itemized-only filter (payee_name, candidate_party, a date or amount bound, is_notice, most_recent, sort, cursor) was supplied alongside mode by_candidate, which cannot apply it Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `by_candidate_requires_scope`: by_candidate mode invoked without a candidate_id and without a full race scope `itemized_only_filters_in_aggregate_mode`: An itemized-only filter (payee_name, candidate_party, a date or amount bound, is_notice, most_recent, sort, cursor) was supplied alongside mode by_candidate, which cannot apply it `inputs_not_applicable_to_mode`: Itemized mode receives an explicit page number that its keyset endpoint cannot apply Other values are possible when a failure originates below the handler." - changed
Output schema / properties / error / properties / data / properties / reason / examplesPrevious value: -[ - "by_candidate_requires_scope", - "itemized_only_filters_in_aggregate_mode" -]New value: +[ + "by_candidate_requires_scope", + "itemized_only_filters_in_aggregate_mode", + "inputs_not_applicable_to_mode" +]
12 tool updates
- Changed
openfec_get_committee_totals6 fields changed- changed
Input schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema" - added
Input schema / additionalPropertiesAdded value: +false - changed
Output schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema" - added
Output schema / anyOfAdded value: +[ + { + "not": { + "required": [ + "error" + ] + }, + "required": [ + "results", + "mode", + "pagination", + "search_criteria", + "totalCount" + ] + }, + { + "required": [ + "error" + ] + } +] - added
Output schema / properties / errorAdded value: +{ + "additionalProperties": {}, + "description": "Present when the call failed. Absent on success.", + "properties": { + "code": { + "description": "JSON-RPC error code for this failure.", + "maximum": 9007199254740991, + "minimum": -9007199254740991, + "type": "integer" + }, + "data": { + "additionalProperties": {}, + "properties": { + "reason": { + "description": "Machine-readable failure mode. Declared by this tool: `committee_id_required_for_single_mode`: Mode single invoked without a committee_id `entity_type_required_for_group_mode`: Mode by_entity_type invoked without an entity_type `inputs_not_applicable_to_mode`: A grouped-search filter (entity_type, committee_state, committee_type, committee_designation, organization_type, or a receipts/disbursements bound) was supplied alongside mode single, which cannot apply it `committee_totals_not_found`: Single-committee lookup matched no totals row — the committee_id does not exist, it filed nothing in the requested cycle, or it has never filed a financial report at all Other values are possible when a failure originates below the handler.", + "examples": [ + "committee_id_required_for_single_mode", + "entity_type_required_for_group_mode", + "inputs_not_applicable_to_mode", + "committee_totals_not_found" + ], + "type": "string" + }, + "recovery": { + "additionalProperties": {}, + "description": "Actionable next step for the caller.", + "properties": { + "hint": { + "type": "string" + } + }, + "required": [ + "hint" + ], + "type": "object" + }, + "retryable": { + "description": "Whether retrying may succeed.", + "type": "boolean" + } + }, + "type": "object" + }, + "message": { + "description": "Human-readable description of what went wrong.", + "type": "string" + } + }, + "required": [ + "code", + "message" + ], + "type": "object" +} - removed
Output schema / requiredRemoved value: -[ - "results", - "mode", - "pagination", - "search_criteria", - "totalCount" -]
- Changed
openfec_get_legal_document6 fields changed- changed
Input schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema" - added
Input schema / additionalPropertiesAdded value: +false - changed
Output schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema" - added
Output schema / anyOfAdded value: +[ + { + "not": { + "required": [ + "error" + ] + }, + "required": [ + "document", + "search_criteria", + "attachedDocumentCount" + ] + }, + { + "required": [ + "error" + ] + } +] - added
Output schema / properties / errorAdded value: +{ + "additionalProperties": {}, + "description": "Present when the call failed. Absent on success.", + "properties": { + "code": { + "description": "JSON-RPC error code for this failure.", + "maximum": 9007199254740991, + "minimum": -9007199254740991, + "type": "integer" + }, + "data": { + "additionalProperties": {}, + "properties": { + "reason": { + "description": "Machine-readable failure mode. Declared by this tool: `legal_document_not_found`: No legal document exists at the requested doc_type and no Other values are possible when a failure originates below the handler.", + "examples": [ + "legal_document_not_found" + ], + "type": "string" + }, + "recovery": { + "additionalProperties": {}, + "description": "Actionable next step for the caller.", + "properties": { + "hint": { + "type": "string" + } + }, + "required": [ + "hint" + ], + "type": "object" + }, + "retryable": { + "description": "Whether retrying may succeed.", + "type": "boolean" + } + }, + "type": "object" + }, + "message": { + "description": "Human-readable description of what went wrong.", + "type": "string" + } + }, + "required": [ + "code", + "message" + ], + "type": "object" +} - removed
Output schema / requiredRemoved value: -[ - "document", - "search_criteria", - "attachedDocumentCount" -]
- Changed
openfec_lookup_calendar6 fields changed- changed
Input schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema" - added
Input schema / additionalPropertiesAdded value: +false - changed
Output schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema" - added
Output schema / anyOfAdded value: +[ + { + "not": { + "required": [ + "error" + ] + }, + "required": [ + "results", + "mode", + "pagination", + "search_criteria", + "totalCount" + ] + }, + { + "required": [ + "error" + ] + } +] - added
Output schema / properties / errorAdded value: +{ + "additionalProperties": {}, + "description": "Present when the call failed. Absent on success.", + "properties": { + "code": { + "description": "JSON-RPC error code for this failure.", + "maximum": 9007199254740991, + "minimum": -9007199254740991, + "type": "integer" + }, + "data": { + "additionalProperties": {}, + "properties": { + "reason": { + "description": "Machine-readable failure mode. Declared by this tool: `inputs_not_applicable_to_mode`: A filter belonging to a different calendar mode was supplied, which the chosen mode cannot apply Other values are possible when a failure originates below the handler.", + "examples": [ + "inputs_not_applicable_to_mode" + ], + "type": "string" + }, + "recovery": { + "additionalProperties": {}, + "description": "Actionable next step for the caller.", + "properties": { + "hint": { + "type": "string" + } + }, + "required": [ + "hint" + ], + "type": "object" + }, + "retryable": { + "description": "Whether retrying may succeed.", + "type": "boolean" + } + }, + "type": "object" + }, + "message": { + "description": "Human-readable description of what went wrong.", + "type": "string" + } + }, + "required": [ + "code", + "message" + ], + "type": "object" +} - removed
Output schema / requiredRemoved value: -[ - "results", - "mode", - "pagination", - "search_criteria", - "totalCount" -]
- Changed
openfec_lookup_elections6 fields changed- changed
Input schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema" - added
Input schema / additionalPropertiesAdded value: +false - changed
Output schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema" - added
Output schema / anyOfAdded value: +[ + { + "not": { + "required": [ + "error" + ] + }, + "required": [ + "results", + "mode", + "pagination", + "search_criteria", + "totalCount" + ] + }, + { + "required": [ + "error" + ] + } +] - added
Output schema / properties / errorAdded value: +{ + "additionalProperties": {}, + "description": "Present when the call failed. Absent on success.", + "properties": { + "code": { + "description": "JSON-RPC error code for this failure.", + "maximum": 9007199254740991, + "minimum": -9007199254740991, + "type": "integer" + }, + "data": { + "additionalProperties": {}, + "properties": { + "reason": { + "description": "Machine-readable failure mode. Declared by this tool: `cycle_must_be_even`: Cycle is an odd year `missing_state_for_office`: Senate or House office without a state and without a zip `missing_district_for_house`: House office without a district number and without a zip `summary_does_not_support_zip`: Summary mode invoked with a zip parameter `inputs_not_applicable_to_mode`: election_full supplied alongside zip — a ZIP-scoped search runs an endpoint that has no such parameter Other values are possible when a failure originates below the handler.", + "examples": [ + "cycle_must_be_even", + "missing_state_for_office", + "missing_district_for_house", + "summary_does_not_support_zip", + "inputs_not_applicable_to_mode" + ], + "type": "string" + }, + "recovery": { + "additionalProperties": {}, + "description": "Actionable next step for the caller.", + "properties": { + "hint": { + "type": "string" + } + }, + "required": [ + "hint" + ], + "type": "object" + }, + "retryable": { + "description": "Whether retrying may succeed.", + "type": "boolean" + } + }, + "type": "object" + }, + "message": { + "description": "Human-readable description of what went wrong.", + "type": "string" + } + }, + "required": [ + "code", + "message" + ], + "type": "object" +} - removed
Output schema / requiredRemoved value: -[ - "results", - "mode", - "pagination", - "search_criteria", - "totalCount" -]
- Changed
openfec_search_candidates6 fields changed- changed
Input schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema" - added
Input schema / additionalPropertiesAdded value: +false - changed
Output schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema" - added
Output schema / anyOfAdded value: +[ + { + "not": { + "required": [ + "error" + ] + }, + "required": [ + "candidates", + "pagination", + "search_criteria", + "totalCount" + ] + }, + { + "required": [ + "error" + ] + } +] - added
Output schema / properties / errorAdded value: +{ + "additionalProperties": {}, + "description": "Present when the call failed. Absent on success.", + "properties": { + "code": { + "description": "JSON-RPC error code for this failure.", + "maximum": 9007199254740991, + "minimum": -9007199254740991, + "type": "integer" + }, + "data": { + "additionalProperties": {}, + "properties": { + "reason": { + "description": "Machine-readable failure mode. Declared by this tool: `candidate_not_found`: Single-candidate lookup by candidate_id returned no record Other values are possible when a failure originates below the handler.", + "examples": [ + "candidate_not_found" + ], + "type": "string" + }, + "recovery": { + "additionalProperties": {}, + "description": "Actionable next step for the caller.", + "properties": { + "hint": { + "type": "string" + } + }, + "required": [ + "hint" + ], + "type": "object" + }, + "retryable": { + "description": "Whether retrying may succeed.", + "type": "boolean" + } + }, + "type": "object" + }, + "message": { + "description": "Human-readable description of what went wrong.", + "type": "string" + } + }, + "required": [ + "code", + "message" + ], + "type": "object" +} - removed
Output schema / requiredRemoved value: -[ - "candidates", - "pagination", - "search_criteria", - "totalCount" -]
- Changed
openfec_search_committees6 fields changed- changed
Input schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema" - added
Input schema / additionalPropertiesAdded value: +false - changed
Output schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema" - added
Output schema / anyOfAdded value: +[ + { + "not": { + "required": [ + "error" + ] + }, + "required": [ + "committees", + "pagination", + "search_criteria", + "totalCount" + ] + }, + { + "required": [ + "error" + ] + } +] - added
Output schema / properties / errorAdded value: +{ + "additionalProperties": {}, + "description": "Present when the call failed. Absent on success.", + "properties": { + "code": { + "description": "JSON-RPC error code for this failure.", + "maximum": 9007199254740991, + "minimum": -9007199254740991, + "type": "integer" + }, + "data": { + "additionalProperties": {}, + "properties": { + "reason": { + "description": "Machine-readable failure mode. Declared by this tool: `committee_not_found`: Single-committee lookup by committee_id returned no record Other values are possible when a failure originates below the handler.", + "examples": [ + "committee_not_found" + ], + "type": "string" + }, + "recovery": { + "additionalProperties": {}, + "description": "Actionable next step for the caller.", + "properties": { + "hint": { + "type": "string" + } + }, + "required": [ + "hint" + ], + "type": "object" + }, + "retryable": { + "description": "Whether retrying may succeed.", + "type": "boolean" + } + }, + "type": "object" + }, + "message": { + "description": "Human-readable description of what went wrong.", + "type": "string" + } + }, + "required": [ + "code", + "message" + ], + "type": "object" +} - removed
Output schema / requiredRemoved value: -[ - "committees", - "pagination", - "search_criteria", - "totalCount" -]
- Changed
openfec_search_contributions6 fields changed- changed
Input schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema" - added
Input schema / additionalPropertiesAdded value: +false - changed
Output schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema" - added
Output schema / anyOfAdded value: +[ + { + "not": { + "required": [ + "error" + ] + }, + "required": [ + "results", + "mode", + "search_criteria", + "totalCount" + ] + }, + { + "required": [ + "error" + ] + } +] - added
Output schema / properties / errorAdded value: +{ + "additionalProperties": {}, + "description": "Present when the call failed. Absent on success.", + "properties": { + "code": { + "description": "JSON-RPC error code for this failure.", + "maximum": 9007199254740991, + "minimum": -9007199254740991, + "type": "integer" + }, + "data": { + "additionalProperties": {}, + "properties": { + "reason": { + "description": "Machine-readable failure mode. Declared by this tool: `itemized_requires_committee_id`: Itemized mode invoked without a committee_id `aggregate_requires_committee_id`: by_employer or by_occupation aggregate without a committee_id `itemized_only_filters_in_aggregate_mode`: An itemized-only filter was supplied alongside an aggregate mode, which cannot apply it Other values are possible when a failure originates below the handler.", + "examples": [ + "itemized_requires_committee_id", + "aggregate_requires_committee_id", + "itemized_only_filters_in_aggregate_mode" + ], + "type": "string" + }, + "recovery": { + "additionalProperties": {}, + "description": "Actionable next step for the caller.", + "properties": { + "hint": { + "type": "string" + } + }, + "required": [ + "hint" + ], + "type": "object" + }, + "retryable": { + "description": "Whether retrying may succeed.", + "type": "boolean" + } + }, + "type": "object" + }, + "message": { + "description": "Human-readable description of what went wrong.", + "type": "string" + } + }, + "required": [ + "code", + "message" + ], + "type": "object" +} - removed
Output schema / requiredRemoved value: -[ - "results", - "mode", - "search_criteria", - "totalCount" -]
- Changed
openfec_search_coordinated_expenditures6 fields changed- changed
Input schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema" - added
Input schema / additionalPropertiesAdded value: +false - changed
Output schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema" - added
Output schema / anyOfAdded value: +[ + { + "not": { + "required": [ + "error" + ] + }, + "required": [ + "results", + "pagination", + "search_criteria", + "totalCount" + ] + }, + { + "required": [ + "error" + ] + } +] - added
Output schema / properties / errorAdded value: +{ + "additionalProperties": {}, + "description": "Present when the call failed. Absent on success.", + "properties": { + "code": { + "description": "JSON-RPC error code for this failure.", + "maximum": 9007199254740991, + "minimum": -9007199254740991, + "type": "integer" + }, + "data": { + "additionalProperties": {}, + "properties": { + "reason": { + "description": "Machine-readable failure mode.", + "type": "string" + }, + "recovery": { + "additionalProperties": {}, + "description": "Actionable next step for the caller.", + "properties": { + "hint": { + "type": "string" + } + }, + "required": [ + "hint" + ], + "type": "object" + }, + "retryable": { + "description": "Whether retrying may succeed.", + "type": "boolean" + } + }, + "type": "object" + }, + "message": { + "description": "Human-readable description of what went wrong.", + "type": "string" + } + }, + "required": [ + "code", + "message" + ], + "type": "object" +} - removed
Output schema / requiredRemoved value: -[ - "results", - "pagination", - "search_criteria", - "totalCount" -]
- Changed
openfec_search_disbursements6 fields changed- changed
Input schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema" - added
Input schema / additionalPropertiesAdded value: +false - changed
Output schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema" - added
Output schema / anyOfAdded value: +[ + { + "not": { + "required": [ + "error" + ] + }, + "required": [ + "results", + "mode", + "search_criteria", + "totalCount" + ] + }, + { + "required": [ + "error" + ] + } +] - added
Output schema / properties / errorAdded value: +{ + "additionalProperties": {}, + "description": "Present when the call failed. Absent on success.", + "properties": { + "code": { + "description": "JSON-RPC error code for this failure.", + "maximum": 9007199254740991, + "minimum": -9007199254740991, + "type": "integer" + }, + "data": { + "additionalProperties": {}, + "properties": { + "reason": { + "description": "Machine-readable failure mode. Declared by this tool: `itemized_only_filters_in_aggregate_mode`: An itemized-only filter was supplied alongside an aggregate mode, which cannot apply it Other values are possible when a failure originates below the handler.", + "examples": [ + "itemized_only_filters_in_aggregate_mode" + ], + "type": "string" + }, + "recovery": { + "additionalProperties": {}, + "description": "Actionable next step for the caller.", + "properties": { + "hint": { + "type": "string" + } + }, + "required": [ + "hint" + ], + "type": "object" + }, + "retryable": { + "description": "Whether retrying may succeed.", + "type": "boolean" + } + }, + "type": "object" + }, + "message": { + "description": "Human-readable description of what went wrong.", + "type": "string" + } + }, + "required": [ + "code", + "message" + ], + "type": "object" +} - removed
Output schema / requiredRemoved value: -[ - "results", - "mode", - "search_criteria", - "totalCount" -]
- Changed
openfec_search_expenditures6 fields changed- changed
Input schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema" - added
Input schema / additionalPropertiesAdded value: +false - changed
Output schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema" - added
Output schema / anyOfAdded value: +[ + { + "not": { + "required": [ + "error" + ] + }, + "required": [ + "results", + "mode", + "search_criteria", + "totalCount" + ] + }, + { + "required": [ + "error" + ] + } +] - added
Output schema / properties / errorAdded value: +{ + "additionalProperties": {}, + "description": "Present when the call failed. Absent on success.", + "properties": { + "code": { + "description": "JSON-RPC error code for this failure.", + "maximum": 9007199254740991, + "minimum": -9007199254740991, + "type": "integer" + }, + "data": { + "additionalProperties": {}, + "properties": { + "reason": { + "description": "Machine-readable failure mode. Declared by this tool: `by_candidate_requires_scope`: by_candidate mode invoked without a candidate_id and without a full race scope `itemized_only_filters_in_aggregate_mode`: An itemized-only filter (payee_name, candidate_party, a date or amount bound, is_notice, most_recent, sort, cursor) was supplied alongside mode by_candidate, which cannot apply it Other values are possible when a failure originates below the handler.", + "examples": [ + "by_candidate_requires_scope", + "itemized_only_filters_in_aggregate_mode" + ], + "type": "string" + }, + "recovery": { + "additionalProperties": {}, + "description": "Actionable next step for the caller.", + "properties": { + "hint": { + "type": "string" + } + }, + "required": [ + "hint" + ], + "type": "object" + }, + "retryable": { + "description": "Whether retrying may succeed.", + "type": "boolean" + } + }, + "type": "object" + }, + "message": { + "description": "Human-readable description of what went wrong.", + "type": "string" + } + }, + "required": [ + "code", + "message" + ], + "type": "object" +} - removed
Output schema / requiredRemoved value: -[ - "results", - "mode", - "search_criteria", - "totalCount" -]
- Changed
openfec_search_filings6 fields changed- changed
Input schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema" - added
Input schema / additionalPropertiesAdded value: +false - changed
Output schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema" - added
Output schema / anyOfAdded value: +[ + { + "not": { + "required": [ + "error" + ] + }, + "required": [ + "results", + "pagination", + "search_criteria", + "totalCount" + ] + }, + { + "required": [ + "error" + ] + } +] - added
Output schema / properties / errorAdded value: +{ + "additionalProperties": {}, + "description": "Present when the call failed. Absent on success.", + "properties": { + "code": { + "description": "JSON-RPC error code for this failure.", + "maximum": 9007199254740991, + "minimum": -9007199254740991, + "type": "integer" + }, + "data": { + "additionalProperties": {}, + "properties": { + "reason": { + "description": "Machine-readable failure mode.", + "type": "string" + }, + "recovery": { + "additionalProperties": {}, + "description": "Actionable next step for the caller.", + "properties": { + "hint": { + "type": "string" + } + }, + "required": [ + "hint" + ], + "type": "object" + }, + "retryable": { + "description": "Whether retrying may succeed.", + "type": "boolean" + } + }, + "type": "object" + }, + "message": { + "description": "Human-readable description of what went wrong.", + "type": "string" + } + }, + "required": [ + "code", + "message" + ], + "type": "object" +} - removed
Output schema / requiredRemoved value: -[ - "results", - "pagination", - "search_criteria", - "totalCount" -]
- Changed
openfec_search_legal6 fields changed- changed
Input schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema" - added
Input schema / additionalPropertiesAdded value: +false - changed
Output schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema" - added
Output schema / anyOfAdded value: +[ + { + "not": { + "required": [ + "error" + ] + }, + "required": [ + "results", + "total_count", + "search_criteria", + "totalCount" + ] + }, + { + "required": [ + "error" + ] + } +] - added
Output schema / properties / errorAdded value: +{ + "additionalProperties": {}, + "description": "Present when the call failed. Absent on success.", + "properties": { + "code": { + "description": "JSON-RPC error code for this failure.", + "maximum": 9007199254740991, + "minimum": -9007199254740991, + "type": "integer" + }, + "data": { + "additionalProperties": {}, + "properties": { + "reason": { + "description": "Machine-readable failure mode. Declared by this tool: `missing_filter`: Called without any scoping filter at all `date_filter_incomplete`: min_date or max_date given without both a type and a date_kind, or a date_kind given with neither bound `date_kind_not_valid_for_type`: The requested date_kind is not a date this document type records Other values are possible when a failure originates below the handler.", + "examples": [ + "missing_filter", + "date_filter_incomplete", + "date_kind_not_valid_for_type" + ], + "type": "string" + }, + "recovery": { + "additionalProperties": {}, + "description": "Actionable next step for the caller.", + "properties": { + "hint": { + "type": "string" + } + }, + "required": [ + "hint" + ], + "type": "object" + }, + "retryable": { + "description": "Whether retrying may succeed.", + "type": "boolean" + } + }, + "type": "object" + }, + "message": { + "description": "Human-readable description of what went wrong.", + "type": "string" + } + }, + "required": [ + "code", + "message" + ], + "type": "object" +} - removed
Output schema / requiredRemoved value: -[ - "results", - "total_count", - "search_criteria", - "totalCount" -]
4 tool updates
- Added
openfec_get_committee_totals - Added
openfec_get_legal_document - Added
openfec_search_coordinated_expenditures - Changed
openfec_search_legal2 fields changed- changed
Output schema / properties / results / items / descriptionPrevious value: -"Legal document record. The document_type field discriminates among advisory_opinion, mur, adr, admin_fine, and statute. Common fields include ao_no/case_no/no (identifier), name, document_type, document_count, and document_categories summarizing the related filings."New value: +"Legal document record. The document_type field discriminates among advisory_opinion, mur, adr, admin_fine, and statute. Common fields include no (the identifier every type carries, and the one openfec_get_legal_document takes; advisory opinions repeat it as ao_no), name, document_type, document_count, and document_categories summarizing the related filings." - added
Output schema / properties / retrievalHintAdded value: +{ + "description": "How to recover the material trimmed out of these results. Present whenever any result was returned, because every result is trimmed.", + "type": "string" +}
9 tool updates
- Changed
openfec_lookup_calendar3 fields changed- added
Output schema / properties / modeAdded value: +{ + "description": "Query mode as the server resolved it. Each mode reads a different FEC dataset with its own row shape — calendar events, report due dates, or election dates — so read this rather than inferring the dataset from the fields present.", + "enum": [ + "events", + "filing_deadlines", + "election_dates" + ], + "type": "string" +} - changed
Output schema / properties / search_criteria / descriptionPrevious value: -"Echo of the search filters that produced this result set. Populated when results are empty to help diagnose why nothing matched."New value: +"Echo of the search filters this call applied, as the server parsed them, minus paging arguments. Always present — compare it against what you sent to confirm every filter was honoured." - changed
Output schema / requiredPrevious value: -[ - "results", - "pagination", - "totalCount" -]New value: +[ + "results", + "mode", + "pagination", + "search_criteria", + "totalCount" +]
- Changed
openfec_lookup_elections5 fields changed- removed
Input schema / properties / election_full / defaultRemoved value: -true - changed
Input schema / properties / election_full / descriptionPrevious value: -"Expand to full election period (4yr president, 6yr senate, 2yr house). Default true. Ignored for ZIP-based searches."New value: +"Expand to full election period (4yr president, 6yr senate, 2yr house). Defaults to true when omitted; a ZIP-scoped search rejects it, since that endpoint has no such parameter. Carries no schema default, so an explicit value is distinguishable from an omission." - added
Output schema / properties / modeAdded value: +{ + "description": "Query mode as the server resolved it. Row shapes differ by mode — search rows are per-candidate financial records, summary is one aggregate race row — so read this rather than inferring the shape from the fields present.", + "enum": [ + "search", + "summary" + ], + "type": "string" +} - changed
Output schema / properties / search_criteria / descriptionPrevious value: -"Echo of the search filters that produced this result set. Populated when results are empty to help diagnose why nothing matched."New value: +"Echo of the search filters this call applied, as the server parsed them, minus paging arguments. Always present — compare it against what you sent to confirm every filter was honoured." - changed
Output schema / requiredPrevious value: -[ - "results", - "pagination", - "totalCount" -]New value: +[ + "results", + "mode", + "pagination", + "search_criteria", + "totalCount" +]
- Changed
openfec_search_candidates2 fields changed- changed
Output schema / properties / search_criteria / descriptionPrevious value: -"Echo of the search filters that produced this result set. Populated when results are empty to help diagnose why nothing matched."New value: +"Echo of the search filters this call applied, as the server parsed them, minus paging arguments. Always present — compare it against what you sent to confirm every filter was honoured." - changed
Output schema / requiredPrevious value: -[ - "candidates", - "pagination", - "totalCount" -]New value: +[ + "candidates", + "pagination", + "search_criteria", + "totalCount" +]
- Changed
openfec_search_committees2 fields changed- changed
Output schema / properties / search_criteria / descriptionPrevious value: -"Echo of the search filters that produced this result set. Populated when results are empty to help diagnose why nothing matched."New value: +"Echo of the search filters this call applied, as the server parsed them, minus paging arguments. Always present — compare it against what you sent to confirm every filter was honoured." - changed
Output schema / requiredPrevious value: -[ - "committees", - "pagination", - "totalCount" -]New value: +[ + "committees", + "pagination", + "search_criteria", + "totalCount" +]
- Changed
openfec_search_contributions4 fields changed- added
Output schema / properties / committeeAdded value: +{ + "additionalProperties": {}, + "description": "The committee every row in this response belongs to, carried once instead of repeated in each row. Present only when the query was scoped to a single committee_id; otherwise each row keeps its own committee object.", + "properties": {}, + "type": "object" +} - added
Output schema / properties / modeAdded value: +{ + "description": "Query mode as the server resolved it. \"by_size\" and \"by_state\" resolve to \"by_size_candidate\" / \"by_state_candidate\" when scoped by candidate_id — a different endpoint with different row shapes — so read this rather than assuming the mode you sent.", + "enum": [ + "itemized", + "by_size", + "by_state", + "by_employer", + "by_occupation", + "by_size_candidate", + "by_state_candidate" + ], + "type": "string" +} - changed
Output schema / properties / search_criteria / descriptionPrevious value: -"Echo of the search filters that produced this result set. Populated when results are empty to help diagnose why nothing matched."New value: +"Echo of the search filters this call applied, as the server parsed them, minus paging arguments. Always present — compare it against what you sent to confirm every filter was honoured." - changed
Output schema / requiredPrevious value: -[ - "results", - "totalCount" -]New value: +[ + "results", + "mode", + "search_criteria", + "totalCount" +]
- Changed
openfec_search_disbursements4 fields changed- added
Output schema / properties / committeeAdded value: +{ + "additionalProperties": {}, + "description": "The committee every row in this response belongs to, carried once instead of repeated in each row. Present only when the query was scoped to a single committee_id; otherwise each row keeps its own committee object.", + "properties": {}, + "type": "object" +} - added
Output schema / properties / modeAdded value: +{ + "description": "Query mode as the server resolved it. Row shapes differ by mode — itemized rows are individual payments, aggregate rows are buckets with a total — so read this rather than inferring the shape from the fields present.", + "enum": [ + "itemized", + "by_purpose", + "by_recipient", + "by_recipient_id" + ], + "type": "string" +} - changed
Output schema / properties / search_criteria / descriptionPrevious value: -"Echo of the search filters that produced this result set. Populated when results are empty to help diagnose why nothing matched."New value: +"Echo of the search filters this call applied, as the server parsed them, minus paging arguments. Always present — compare it against what you sent to confirm every filter was honoured." - changed
Output schema / requiredPrevious value: -[ - "results", - "totalCount" -]New value: +[ + "results", + "mode", + "search_criteria", + "totalCount" +]
- Changed
openfec_search_expenditures6 fields changed- removed
Input schema / properties / most_recent / defaultRemoved value: -true - changed
Input schema / properties / most_recent / descriptionPrevious value: -"Only the most recent version of amended filings. Itemized only."New value: +"Only the most recent version of amended filings. Itemized only — by_candidate rejects it. Defaults to true in itemized mode when omitted; pass false to see superseded versions of amended filings." - added
Output schema / properties / committeeAdded value: +{ + "additionalProperties": {}, + "description": "The committee every row in this response belongs to, carried once instead of repeated in each row. Present only when the query was scoped to a single committee_id; otherwise each row keeps its own committee object.", + "properties": {}, + "type": "object" +} - added
Output schema / properties / modeAdded value: +{ + "description": "Query mode as the server resolved it. Row shapes differ by mode — itemized rows are individual expenditures, by_candidate rows are per-candidate totals — so read this rather than inferring the shape from the fields present.", + "enum": [ + "itemized", + "by_candidate" + ], + "type": "string" +} - changed
Output schema / properties / search_criteria / descriptionPrevious value: -"Echo of the search filters that produced this result set. Populated when results are empty to help diagnose why nothing matched."New value: +"Echo of the search filters this call applied, as the server parsed them, minus paging arguments. Always present — compare it against what you sent to confirm every filter was honoured." - changed
Output schema / requiredPrevious value: -[ - "results", - "totalCount" -]New value: +[ + "results", + "mode", + "search_criteria", + "totalCount" +]
- Changed
openfec_search_filings2 fields changed- changed
Output schema / properties / search_criteria / descriptionPrevious value: -"Echo of the search filters that produced this result set. Populated when results are empty to help diagnose why nothing matched."New value: +"Echo of the search filters this call applied, as the server parsed them, minus paging arguments. Always present — compare it against what you sent to confirm every filter was honoured." - changed
Output schema / requiredPrevious value: -[ - "results", - "pagination", - "totalCount" -]New value: +[ + "results", + "pagination", + "search_criteria", + "totalCount" +]
- Changed
openfec_search_legal2 fields changed- changed
Output schema / properties / search_criteria / descriptionPrevious value: -"Echo of the search filters that produced this result set. Populated when results are empty to help diagnose why nothing matched."New value: +"Echo of the search filters this call applied, as the server parsed them, minus paging arguments. Always present — compare it against what you sent to confirm every filter was honoured." - changed
Output schema / requiredPrevious value: -[ - "results", - "total_count", - "totalCount" -]New value: +[ + "results", + "total_count", + "search_criteria", + "totalCount" +]
3 tool updates
- Changed
openfec_search_disbursements1 field changed- changed
Input schema / properties / cycle / descriptionPrevious value: -"Two-year election cycle (e.g., 2024). Even years only."New value: +"Two-year election cycle (e.g., 2024). Even years only. Itemized mode defaults to the current cycle when omitted — Schedule B spans all history, and an all-history scan of an active committee times out upstream. Pass an explicit cycle to search an earlier period."
- Changed
openfec_search_expenditures5 fields changed- changed
Input schema / properties / candidate_office / descriptionPrevious value: -"Office of the targeted candidate: H=House, S=Senate, P=President."New value: +"Office of the targeted candidate: H=House, S=Senate, P=President. In by_candidate mode this scopes a whole race: P stands alone, S also needs candidate_office_state, H also needs candidate_office_state and candidate_office_district." - added
Input schema / properties / candidate_office_districtAdded value: +{ + "description": "Two-digit House district of the targeted race (e.g., \"09\"). Required alongside candidate_office=H and candidate_office_state in by_candidate mode; Senate and presidential rows carry no district and match nothing when one is supplied.", + "type": "string" +} - changed
Input schema / properties / candidate_office_state / descriptionPrevious value: -"Two-letter state code of the targeted race."New value: +"Two-letter state code of the targeted race. Required alongside candidate_office=H or candidate_office=S in by_candidate mode; leave it off for candidate_office=P, whose aggregate rows carry no state and match nothing when one is supplied." - changed
Input schema / properties / candidate_party / descriptionPrevious value: -"Three-letter party code of the targeted candidate (e.g., DEM, REP)."New value: +"Three-letter party code of the targeted candidate (e.g., DEM, REP). Itemized only — by_candidate rejects it, since the aggregate endpoint has no party filter." - changed
Input schema / properties / cycle / descriptionPrevious value: -"Two-year election cycle (e.g., 2024). Even years only."New value: +"Two-year election cycle (e.g., 2024). Even years only. Itemized mode defaults to the current cycle when omitted — Schedule E spans all history and an unscoped scan times out upstream. Pass an explicit cycle to search an earlier period."
- Changed
openfec_search_legal5 fields changed- added
Input schema / properties / date_kindAdded value: +{ + "description": "Which date min_date/max_date bound. Each document type records its own dates, so this must be one the chosen type has: type=advisory_opinions → issue_date (opinion issued), request_date (request received), document_date; type=murs or adrs → open_date (case opened), close_date (case closed), document_date; type=admin_fines → rtb_date (reason-to-believe finding), fd_date (final determination). type=statutes cannot be date-filtered. Required whenever min_date or max_date is given, together with type.", + "enum": [ + "issue_date", + "request_date", + "open_date", + "close_date", + "document_date", + "rtb_date", + "fd_date" + ], + "type": "string" +} - changed
Input schema / properties / max_date / descriptionPrevious value: -"Latest document date (YYYY-MM-DD)."New value: +"Latest date (YYYY-MM-DD) for the date_kind selected. Requires type and date_kind." - changed
Input schema / properties / max_penalty_amount / descriptionPrevious value: -"Maximum penalty amount."New value: +"Maximum penalty amount in dollars. Filters enforcement cases (murs, adrs) only — other document types are returned unfiltered by it." - changed
Input schema / properties / min_date / descriptionPrevious value: -"Earliest document date (YYYY-MM-DD)."New value: +"Earliest date (YYYY-MM-DD) for the date_kind selected. Requires type and date_kind." - changed
Input schema / properties / min_penalty_amount / descriptionPrevious value: -"Minimum penalty amount (enforcement cases)."New value: +"Minimum penalty amount in dollars. Filters enforcement cases (murs, adrs) only — other document types are returned unfiltered by it."
5 tool updates
- Changed
openfec_lookup_elections2 fields changed- added
Input schema / properties / pageAdded value: +{ + "default": 1, + "description": "Page number (1-indexed). Search mode only — summary mode returns a single aggregate row. Read pagination.pages in the response to see how many pages exist.", + "maximum": 9007199254740991, + "minimum": 1, + "type": "integer" +} - added
Input schema / properties / per_pageAdded value: +{ + "default": 20, + "description": "Results per page. Search mode only.", + "maximum": 100, + "minimum": 1, + "type": "integer" +}
- Changed
openfec_search_candidates2 fields changed- added
Output schema / properties / missing_totalsAdded value: +{ + "description": "Candidates whose financial totals were not retrieved because the totals fetch hit its page cap. Re-query each one on its own with candidate_id to get its totals.", + "items": { + "description": "FEC candidate ID with no totals row in this response.", + "type": "string" + }, + "type": "array" +} - changed
Output schema / properties / totals / descriptionPrevious value: -"Financial totals (receipts, disbursements, cash_on_hand) when include_totals is true."New value: +"Financial totals (receipts, disbursements, cash_on_hand) when include_totals is true. One row per candidate per cycle."
- Changed
openfec_search_contributions1 field changed- added
Input schema / properties / pageAdded value: +{ + "default": 1, + "description": "Page number (1-indexed) for the aggregate modes. Ignored in itemized mode, which paginates with cursor. Read pagination.pages in the response to see how many pages exist.", + "maximum": 9007199254740991, + "minimum": 1, + "type": "integer" +}
- Changed
openfec_search_disbursements1 field changed- added
Input schema / properties / pageAdded value: +{ + "default": 1, + "description": "Page number (1-indexed) for the aggregate modes. Ignored in itemized mode, which paginates with cursor. Read pagination.pages in the response to see how many pages exist.", + "maximum": 9007199254740991, + "minimum": 1, + "type": "integer" +}
- Changed
openfec_search_expenditures1 field changed- added
Input schema / properties / pageAdded value: +{ + "default": 1, + "description": "Page number (1-indexed) for by_candidate mode. Ignored in itemized mode, which paginates with cursor. Read pagination.pages in the response to see how many pages exist.", + "maximum": 9007199254740991, + "minimum": 1, + "type": "integer" +}
3 tool updates
- Changed
openfec_search_contributions3 fields changed- changed
Input schema / properties / cursor / descriptionPrevious value: -"Opaque pagination cursor from a previous response. Itemized mode only (keyset pagination)."New value: +"Opaque pagination cursor from a previous response of this tool. Itemized mode only (keyset pagination). Valid only for an otherwise-identical call — changing any other argument, including sort, rejects the cursor; omit it to start over." - changed
Input schema / properties / sort / descriptionPrevious value: -"Sort field. Itemized only."New value: +"Sort field. A \"-\" prefix sorts descending: use \"-contribution_receipt_amount\" for the largest receipts first, since the ascending form leads with the most negative rows (refunds, reattributions, redesignations). Itemized only; OpenFEC sorts by \"-contribution_receipt_date\" when omitted." - changed
Input schema / properties / sort / enumPrevious value: -[ - "contribution_receipt_date", - "contribution_receipt_amount" -]New value: +[ + "contribution_receipt_date", + "-contribution_receipt_date", + "contribution_receipt_amount", + "-contribution_receipt_amount" +]
- Changed
openfec_search_disbursements3 fields changed- changed
Input schema / properties / cursor / descriptionPrevious value: -"Opaque pagination cursor from a previous response. Itemized mode only (keyset pagination)."New value: +"Opaque pagination cursor from a previous response of this tool. Itemized mode only (keyset pagination). Valid only for an otherwise-identical call — changing any other argument, including sort, rejects the cursor; omit it to start over." - changed
Input schema / properties / sort / descriptionPrevious value: -"Sort field. Itemized only."New value: +"Sort field. A \"-\" prefix sorts descending: use \"-disbursement_amount\" for the biggest payments first, since the ascending form leads with the most negative rows (refunds and voided payments). Itemized only; OpenFEC sorts by \"-disbursement_date\" when omitted." - changed
Input schema / properties / sort / enumPrevious value: -[ - "disbursement_date", - "disbursement_amount" -]New value: +[ + "disbursement_date", + "-disbursement_date", + "disbursement_amount", + "-disbursement_amount" +]
- Changed
openfec_search_expenditures3 fields changed- changed
Input schema / properties / cursor / descriptionPrevious value: -"Opaque pagination cursor from a previous response. Itemized mode only (keyset pagination)."New value: +"Opaque pagination cursor from a previous response of this tool. Itemized mode only (keyset pagination). Valid only for an otherwise-identical call — changing any other argument, including sort, rejects the cursor; omit it to start over." - changed
Input schema / properties / sort / descriptionPrevious value: -"Sort field. Itemized only."New value: +"Sort field. A \"-\" prefix sorts descending: use \"-expenditure_amount\" for the largest outside spending first, since the ascending form leads with the most negative rows (corrections and voided entries). Itemized only; OpenFEC sorts by \"-expenditure_date\" when omitted." - changed
Input schema / properties / sort / enumPrevious value: -[ - "expenditure_date", - "expenditure_amount", - "office_total_ytd" -]New value: +[ + "expenditure_date", + "-expenditure_date", + "expenditure_amount", + "-expenditure_amount", + "office_total_ytd", + "-office_total_ytd" +]
6 tool updates
- Changed
openfec_search_candidates1 field changed- removed
Input schema / properties / candidate_id / patternRemoved value: -"^[HSP][0-9A-Z]+$"
- Changed
openfec_search_committees2 fields changed- removed
Input schema / properties / candidate_id / patternRemoved value: -"^[HSP][0-9A-Z]+$" - removed
Input schema / properties / committee_id / patternRemoved value: -"^C\\d+$"
- Changed
openfec_search_contributions2 fields changed- removed
Input schema / properties / candidate_id / patternRemoved value: -"^[HSP][0-9A-Z]+$" - removed
Input schema / properties / committee_id / patternRemoved value: -"^C\\d+$"
- Changed
openfec_search_disbursements1 field changed- removed
Input schema / properties / committee_id / patternRemoved value: -"^C\\d+$"
- Changed
openfec_search_expenditures2 fields changed- removed
Input schema / properties / candidate_id / patternRemoved value: -"^[HSP][0-9A-Z]+$" - removed
Input schema / properties / committee_id / patternRemoved value: -"^C\\d+$"
- Changed
openfec_search_filings2 fields changed- removed
Input schema / properties / candidate_id / patternRemoved value: -"^[HSP][0-9A-Z]+$" - removed
Input schema / properties / committee_id / patternRemoved value: -"^C\\d+$"
1 tool update
- Changed
openfec_search_legal2 fields changed- added
Output schema / properties / totalCountAdded value: +{ + "description": "Total matching legal documents across all types.", + "type": "number" +} - changed
Output schema / requiredPrevious value: -[ - "results", - "total_count" -]New value: +[ + "results", + "total_count", + "totalCount" +]
9 tool updates
- Changed
openfec_lookup_calendar3 fields changed- added
Output schema / properties / noticeAdded value: +{ + "description": "Guidance when no calendar entries matched — echoes filters and suggests how to broaden.", + "type": "string" +} - added
Output schema / properties / totalCountAdded value: +{ + "description": "Total matching calendar entries before pagination.", + "type": "number" +} - changed
Output schema / requiredPrevious value: -[ - "results", - "pagination" -]New value: +[ + "results", + "pagination", + "totalCount" +]
- Changed
openfec_lookup_elections3 fields changed- added
Output schema / properties / noticeAdded value: +{ + "description": "Guidance when no election results matched — echoes filters and suggests how to broaden.", + "type": "string" +} - added
Output schema / properties / totalCountAdded value: +{ + "description": "Total matching candidates or race summaries.", + "type": "number" +} - changed
Output schema / requiredPrevious value: -[ - "results", - "pagination" -]New value: +[ + "results", + "pagination", + "totalCount" +]
- Changed
openfec_search_candidates3 fields changed- added
Output schema / properties / noticeAdded value: +{ + "description": "Guidance when no candidates matched — echoes filters and suggests how to broaden.", + "type": "string" +} - added
Output schema / properties / totalCountAdded value: +{ + "description": "Total matching candidates before pagination.", + "type": "number" +} - changed
Output schema / requiredPrevious value: -[ - "candidates", - "pagination" -]New value: +[ + "candidates", + "pagination", + "totalCount" +]
- Changed
openfec_search_committees3 fields changed- added
Output schema / properties / noticeAdded value: +{ + "description": "Guidance when no committees matched — echoes filters and suggests how to broaden.", + "type": "string" +} - added
Output schema / properties / totalCountAdded value: +{ + "description": "Total matching committees before pagination.", + "type": "number" +} - changed
Output schema / requiredPrevious value: -[ - "committees", - "pagination" -]New value: +[ + "committees", + "pagination", + "totalCount" +]
- Changed
openfec_search_contributions3 fields changed- added
Output schema / properties / noticeAdded value: +{ + "description": "Guidance when no contributions matched — echoes filters and suggests how to broaden.", + "type": "string" +} - added
Output schema / properties / totalCountAdded value: +{ + "description": "Total matching contributions or aggregate rows.", + "type": "number" +} - changed
Output schema / requiredPrevious value: -[ - "results" -]New value: +[ + "results", + "totalCount" +]
- Changed
openfec_search_disbursements3 fields changed- added
Output schema / properties / noticeAdded value: +{ + "description": "Guidance when no disbursements matched — echoes filters and suggests how to broaden.", + "type": "string" +} - added
Output schema / properties / totalCountAdded value: +{ + "description": "Total matching disbursements or aggregate rows.", + "type": "number" +} - changed
Output schema / requiredPrevious value: -[ - "results" -]New value: +[ + "results", + "totalCount" +]
- Changed
openfec_search_expenditures3 fields changed- added
Output schema / properties / noticeAdded value: +{ + "description": "Guidance when no expenditures matched — echoes filters and suggests how to broaden.", + "type": "string" +} - added
Output schema / properties / totalCountAdded value: +{ + "description": "Total matching expenditures or per-candidate aggregates.", + "type": "number" +} - changed
Output schema / requiredPrevious value: -[ - "results" -]New value: +[ + "results", + "totalCount" +]
- Changed
openfec_search_filings3 fields changed- added
Output schema / properties / noticeAdded value: +{ + "description": "Guidance when no filings matched — echoes filters and suggests how to broaden.", + "type": "string" +} - added
Output schema / properties / totalCountAdded value: +{ + "description": "Total matching filings before pagination.", + "type": "number" +} - changed
Output schema / requiredPrevious value: -[ - "results", - "pagination" -]New value: +[ + "results", + "pagination", + "totalCount" +]
- Changed
openfec_search_legal1 field changed- added
Output schema / properties / noticeAdded value: +{ + "description": "Guidance when no legal documents matched — echoes filters and suggests how to broaden.", + "type": "string" +}
6 tool updates
- Changed
openfec_search_candidates2 fields changed- changed
Input schema / properties / candidate_id / descriptionPrevious value: -"FEC candidate ID (e.g., P00003392, H2CO07170). When provided, returns a single candidate with full detail."New value: +"FEC candidate ID (e.g., P00003392, H2CO07170). Get IDs from openfec_search_candidates results. When provided, returns a single candidate with full detail." - added
Input schema / properties / candidate_id / patternAdded value: +"^[HSP][0-9A-Z]+$"
- Changed
openfec_search_committees4 fields changed- changed
Input schema / properties / candidate_id / descriptionPrevious value: -"Find committees linked to this candidate (authorized, leadership, joint fundraising)."New value: +"Find committees linked to this candidate (authorized, leadership, joint fundraising). Get IDs from openfec_search_candidates results." - added
Input schema / properties / candidate_id / patternAdded value: +"^[HSP][0-9A-Z]+$" - changed
Input schema / properties / committee_id / descriptionPrevious value: -"FEC committee ID (e.g., C00358796). Starts with 'C' followed by digits. Returns a single committee with full detail."New value: +"FEC committee ID (e.g., C00358796). Get IDs from openfec_search_committees results. Starts with 'C' followed by digits. Returns a single committee with full detail." - added
Input schema / properties / committee_id / patternAdded value: +"^C\\d+$"
- Changed
openfec_search_contributions4 fields changed- changed
Input schema / properties / candidate_id / descriptionPrevious value: -"Candidate ID. Enables by_size and by_state aggregates without a committee_id."New value: +"Candidate ID (e.g., P00003392). Get IDs from openfec_search_candidates results. Enables by_size and by_state aggregates without a committee_id." - added
Input schema / properties / candidate_id / patternAdded value: +"^[HSP][0-9A-Z]+$" - changed
Input schema / properties / committee_id / descriptionPrevious value: -"Receiving committee ID (e.g., C00703975)."New value: +"Receiving committee ID (e.g., C00703975). Get IDs from openfec_search_committees results." - added
Input schema / properties / committee_id / patternAdded value: +"^C\\d+$"
- Changed
openfec_search_disbursements2 fields changed- changed
Input schema / properties / committee_id / descriptionPrevious value: -"Spending committee ID (e.g., C00703975). Required for all modes."New value: +"Spending committee ID (e.g., C00703975). Get IDs from openfec_search_committees results. Required for all modes." - added
Input schema / properties / committee_id / patternAdded value: +"^C\\d+$"
- Changed
openfec_search_expenditures4 fields changed- changed
Input schema / properties / candidate_id / descriptionPrevious value: -"Targeted candidate ID (e.g., P00003392)."New value: +"Targeted candidate ID (e.g., P00003392). Get IDs from openfec_search_candidates results." - added
Input schema / properties / candidate_id / patternAdded value: +"^[HSP][0-9A-Z]+$" - changed
Input schema / properties / committee_id / descriptionPrevious value: -"Spending committee ID (e.g., C00703975)."New value: +"Spending committee ID (e.g., C00703975). Get IDs from openfec_search_committees results." - added
Input schema / properties / committee_id / patternAdded value: +"^C\\d+$"
- Changed
openfec_search_filings4 fields changed- changed
Input schema / properties / candidate_id / descriptionPrevious value: -"Associated candidate ID."New value: +"Associated candidate ID (e.g., P00003392). Get IDs from openfec_search_candidates results." - added
Input schema / properties / candidate_id / patternAdded value: +"^[HSP][0-9A-Z]+$" - changed
Input schema / properties / committee_id / descriptionPrevious value: -"Filing committee ID."New value: +"Filing committee ID (e.g., C00358796). Get IDs from openfec_search_committees results." - added
Input schema / properties / committee_id / patternAdded value: +"^C\\d+$"
Related MCP Connectors
FEC campaign finance data: candidate fundraising, donors, and spending
OpenFEC MCP — Federal Election Commission campaign finance data
Access US federal award, recipient, agency, and spending analytics data from USAspending.gov.
U.S. federal policy data — bills, Congress members, voting records, and civic info.
Related MCP Servers
- AlicenseAqualityBmaintenanceQuery FEC campaign finance data — search candidates, track donations, analyze spending, and monitor Super PAC activity via the OpenFEC API.82 npm4MIT
- AlicenseNot gradedqualityDmaintenanceConnects the OpenFEC API to AI assistants for investigating US federal campaign finance through natural language conversations.1MIT
- AlicenseNot gradedqualityCmaintenanceAccess Federal Election Commission campaign finance data through MCP tools. Enables querying OpenFEC data using natural language via ask_pipeworx or direct tool calls.2 npmMIT
- AlicenseNot gradedqualityDmaintenanceEnables searching political donations, donors, and lobbying data from any AI assistant using Federal Election Commission data.6 npmMIT
Glama MCP Gateway
Add one secure layer between your agents and this server.