Georgia's Code, bills, Supreme Court opinions, and 2026 House and Senate meetings. Independent.
Scored across 5 tools
Each tool has a clearly distinct role: describe_site handles orientation and id grammar, get_coverage reports holdings and gaps, search discovers documents, fetch retrieves known documents or parts, and verify_quote checks quotations. The boundary between describe_site and get_coverage is especially clear because one explains how the system works while the other reports what is currently held.
Most names follow a snake_case verb_noun pattern (describe_site, get_coverage, verify_quote), but search and fetch are bare verbs. The convention is still readable and predictable overall, with only minor deviations.
Five tools is well-scoped for a legal research server: orientation, search, retrieval, coverage, and quotation verification. Each tool earns its place, and broader functionality is handled through parameters rather than by fragmenting into many narrow tools.
The surface covers the full read-only research lifecycle: understanding the system, searching across all collections, fetching documents and versions, checking coverage and known gaps, and verifying quotations. There are no obvious missing operations for the stated purpose.
Orientation: what Georgia Commons is, the id grammar, the filter values, and the bodies. Call it first.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so the safety profile is covered. The description adds that the payload is explanatory reference content rather than data records, which is useful, but with no output schema it never indicates the shape or volume of what comes back. That gap keeps it at an adequate-but-thin 3.
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?
One front-loaded sentence with a label ('Orientation:') followed by the actionable directive 'Call it first' — nothing is padded. The only weakness is that the enumerated topics are compressed into terse nouns, notably the unexplained 'bodies'.
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 zero-parameter, read-only, annotation-rich documentation tool with no output schema, the description covers the essentials: what it contains and that it should precede other calls. Only the vagueness of 'the bodies' and the absence of any hint about return size prevent a 5.
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 tool takes zero parameters, so there is nothing for the description to disambiguate and the baseline of 4 applies. The description correctly implies a no-argument call by instructing the agent to just call it first.
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 frames the tool as orientation material covering four concrete topics (what Georgia Commons is, id grammar, filter values, bodies), which is clearly distinct from the action-oriented siblings fetch/search/verify_quote. The noun 'the bodies' is undefined, leaving one listed component opaque, so it stops short of a fully precise purpose statement.
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?
'Call it first' gives explicit, unambiguous ordering guidance that no sibling could provide, effectively telling the agent this is a prerequisite read. It does not name when to skip it or how it relates to each sibling beyond ordering, so it lacks true when-not guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Read one document by id or any written form (bill:2025-2026/hb136, SB 3, opinion:S26A0060, 317 Ga. 528, code:16-11-127, O.C.G.A. § 16-11-127, ga-const:art-i-sec-i-para-iii, meeting:2026-02-05/house-rules, a page URL) as Markdown, at most max_chars (default 60,000) from start, with a pointer to the rest. metadata lists its versions, links grouped by relation, and parts (part reads one: a bill's votes or history, a meeting's transcript). A version id (...@key) reads that version. A hierarchy node (code:t16, code:t16/c11, ga-const:art-i) returns its children. A bill number used in more than one session returns the choices. around takes a passage citation from search and returns the text around it.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | A document id or any written form of one (a bill number, docket, citation, page URL), a version id, or a hierarchy node. | |
| part | No | document (default), or one of the parts metadata.parts lists. | document |
| start | No | Character offset to read from (the pointer at the end of a window gives it). | |
| around | No | A passage citation from search (version_id#start-end): the text around it. | |
| include | No | Parts to add to metadata (e.g. votes, history). | |
| max_chars | No | Characters to return, 1,000 to 200,000. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly/idempotent/non-destructive, and the description adds substantial behavior beyond them: default and maximum window sizes, truncation with a continuation pointer, ambiguity resolution (a bill number in multiple sessions returns choices), version-id reading via `...@key`, and hierarchy expansion. These are the exact runtime traits an agent cannot infer from structured fields.
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?
One dense paragraph, front-loaded with the primary operation before the mode variants, and no filler sentences. It is close to the upper limit of density — clauses like "A version id (`...@key`) reads that version" are terse to the point of requiring a second read.
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?
There is no output schema, so the description carries the return-value burden and does so: Markdown body, `max_chars` window, continuation pointer, and the metadata payload (versions, links by relation, parts). For a six-parameter read tool with four distinct modes, nothing an agent needs to invoke 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?
Schema coverage is 100%, so baseline would be 3, but the description adds real meaning: concrete `part` values (a bill's votes or history, a meeting's transcript), the `start`/pointer relationship for paging, and the `around` argument's provenance from search citations. Only `include` is left mostly to 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?
Opens with a specific verb and resource ('Read one document') and immediately enumerates the id forms it accepts, which makes it trivially distinguishable from search, describe_site, and verify_quote. An agent knows exactly what this tool returns (Markdown) and on what object.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Usage contexts are spelled out well: use `around` with a passage citation from search, use `metadata` to enumerate versions/links/parts, use `part` to pull a bill's votes or a meeting's transcript, and hierarchy nodes return children. What's missing is an explicit statement of when to prefer this over search or verify_quote, or an exclusion for oversized documents.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
What Georgia Commons holds, computed now: each source's documents by type and issuing body, date ranges, how much is searchable by meaning, the last update, the qualifications, and what is not held yet (local governments, school boards, the Court of Appeals). Filters narrow it.
| Name | Required | Description | Default |
|---|---|---|---|
| filters | No | Optional: narrow to document types, bodies, kinds of body, levels. |
| Name | Required | Description |
|---|---|---|
| entries | Yes | |
| not_held | No | |
| not_held_yet | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds genuine context beyond them: the numbers are 'computed now' (freshly calculated, not cached), and the result deliberately includes qualifications and explicitly absent coverage (local governments, school boards, Court of Appeals), which tells the agent to expect caveats rather than a bare count.
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 resource and its live nature, then the narrowing note. The middle enumeration is long but every clause corresponds to a distinct part of the report, so it earns its place; it could be tightened slightly by grouping the related date/coverage items.
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 an output schema handling return format and annotations handling safety, the description covers what an agent needs to decide and call correctly: what is measured, that it is current, that gaps and qualifications are included, and that filters can narrow scope. Nothing material is missing for a single-optional-parameter read tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% and the single filters object is thoroughly documented with vocabularies, defaults, and enum meanings (place_scope, include_overlapping, date_field). The description only says 'Filters narrow it,' adding no syntax or semantics beyond the schema, so the baseline 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description names a concrete artifact — a live coverage report of each source's documents by type, issuing body, date ranges, semantic-searchability, last update, and known gaps. It is clearly not fetch/search, but it never explicitly names or contrasts with the siblings (describe_site, search, fetch, verify_quote), so differentiation is by inference rather than statement.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Usage is only implied: 'Filters narrow it' and the mention of what is not held suggest a pre-search orientation step, but there is no explicit statement of when to call this versus describe_site or search. The strongest routing hint (describe_site lists body ids) lives in the schema, not the description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search every collection at once: Georgia General Assembly bills (every version) and amendments, Supreme Court of Georgia opinions, the Official Code of Georgia Annotated and the Georgia and U.S. constitutions, and machine transcripts of House and Senate meetings. Plain-language questions work: results are ranked by meaning as well as by words. Returns documents with their best passages (each with a citation version_id#start-end and a deep link), facet counts to narrow by, the interpretation used (identifiers found, places, bodies), a confidence band, and coverage notes that say when the records asked about are not held. Empty query with filters browses. mode: all lists every match found, sorted by date, a page at a time with cursor and a total of what was found.
| Name | Required | Description | Default |
|---|---|---|---|
| mode | No | best: ranked and cut. all: every match found, by date, paged, with a total. | best |
| sort | No | Result order. | relevance |
| limit | No | Results per page: 1 to 50 (default 10 documents; 25 in mode all). | |
| query | No | A question or keywords, in plain language. Empty with filters: browse. | |
| cursor | No | The next_cursor of a previous call, for the next page. | |
| parent | No | Only documents inside this hierarchy node (code:t16, code:t16/c11, ga-const:art-i). | |
| filters | No | Optional hard filters (see describe_site for values). | |
| versions | No | current (default) or all versions (how a bill changed). | current |
| linked_to | No | Only documents linked to this document id (a bill's meetings, a section's amending bills). | |
| relations | No | With linked_to: relation types (discusses, amends, amendment_to, cites, ...). |
| Name | Required | Description |
|---|---|---|
| query | Yes | |
| total | No | |
| facets | No | |
| results | Yes | |
| confidence | No | |
| total_kind | No | |
| next_cursor | No | |
| coverage_notes | No | |
| interpretation | No | |
| documents_found | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly/idempotent/openWorld, so the description rightly spends its budget on richer traits: semantic-plus-lexical ranking, passage-level results with `version_id#start-end` citations and deep links, facet counts, interpretation echo, a confidence band, and coverage notes that disclose when records are not held. That coverage-note disclosure is genuinely behavior-level information an agent cannot infer. It does not cover rate limits or performance characteristics, keeping it below 5.
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?
Front-loaded with the collection scope, then usage, then return shape, then the mode distinction — a sensible order with no wasted preamble. It is dense to the point of being a single run-on chain, and the `mode: all` sentence partly duplicates the schema's `mode` field description.
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 an output schema present and 100% param coverage, the description only needs to frame scope and behavior, which it does, including the pointer to describe_site for filter vocabularies. The one gap is relationship parameters: `linked_to` and `relations` get no mention in prose, leaving an agent to rely entirely on schema text for the graph-traversal capability.
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 every parameter including the enum semantics of `mode`, `sort`, `versions`, and the full Filters object. The description adds only the browse-on-empty-query rule and a restatement of `mode: all` paging that the schema's own field description already provides. Baseline 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb and a precisely enumerated resource set: bills and amendments, Supreme Court opinions, code and constitutions, and House/Senate transcripts. An agent can tell instantly that this is the broad cross-collection retrieval tool, distinct from the single-document siblings fetch and verify_quote.
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?
Gives concrete usage contexts: plain-language questions are supported, and an empty `query` with filters browses. It also carves out `mode: all` as the exhaustive-listing path. It stops short of stating when NOT to use it or pointing to fetch/verify_quote for known-document retrieval, so no explicit alternative routing.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Check whether a quotation appears word for word in a stored document (or one version of it), after normalizing whitespace, typographic quotes and dashes, [T]he-style alterations, amendment marks, and case. Use it before relying on a quotation.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | The document id (or any written form of one). | |
| quote | Yes | The quotation to check, at least 12 characters. | |
| version | No | A version id to check; default the current version, then earlier ones. |
| Name | Required | Description |
|---|---|---|
| id | Yes | |
| in | No | |
| chars | Yes | |
| found | Yes | |
| md_url | Yes | |
| current | No | |
| version_id | No | |
| occurrences | Yes | |
| canonical_url | Yes | |
| version_label | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so safety is covered. The description earns credit for disclosing non-obvious matching behavior beyond the annotations: normalization of whitespace, typographic quotes and dashes, [T]he-style alterations, amendment marks, and case, plus the current-version-then-earlier-versions fallback. It does not describe the result shape, but an output schema exists to carry that.
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 check and its normalization caveats, then a short usage clause. Slightly clunky with the bracketed '[T]he-style alterations' fragment and the trailing '(or one version of it)', but nothing is genuinely redundant.
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 read-only verification tool with rich annotations, a fully documented schema, and an output schema, the description covers what an agent needs: what is compared, how normalization affects matching, and the version scope. It could say more about what a failed match implies (e.g. that amendment marks make near-misses expected), but no essential calling information 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% and all three parameters are documented in the schema, including the version fallback and the 12-character quote minimum. The description adds no syntax or format detail for id, quote or version beyond what the schema already states, so the baseline of 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb and resource: 'Check whether a quotation appears word for word in a stored document (or one version of it)'. It also scopes the comparison semantics, so an agent can tell this apart from the sibling retrieval tools (search, fetch, describe_site, get_coverage) without opening the schema.
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?
'Use it before relying on a quotation' gives a clear usage context, and the verification framing makes the intent unambiguous. It stops short of naming exclusions or pointing at an alternative path (e.g. what to do when the quote is not found, or when to use search instead), so it lands at 4 rather than 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
bills_get_textbills_listbills_lookupbills_searchcode_browsecode_describe_structurecode_find_actcode_find_chaptercode_get_chaptercode_lookup_sectioncode_lookup_sectionscode_searchconstitution_browseconstitution_lookupfetch8 fields changedInput schema / properties / aroundAdded value: +{
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "description": "A passage citation from search (version_id#start-end): the text around it.",
+ "title": "Around"
+}Input schema / properties / fullRemoved value: -{
- "default": false,
- "description": "Include the optional material the tool describes (for example votes and history, or the notes). Longer.",
- "title": "Full",
- "type": "boolean"
-}Input schema / properties / id / descriptionPrevious value: -"A document id from search: code:44-7-34, ga-const:art-i-sec-i-para-i, us-const:amend-xiv, bill:2025-2026/hb136, opinion:S26A0060, or meeting:2026-02-05/house-rules."New value: +"A document id or any written form of one (a bill number, docket, citation, page URL), a version id, or a hierarchy node."Input schema / properties / id / maxLengthAdded value: +300Input schema / properties / includeAdded value: +{
+ "anyOf": [
+ {
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "description": "Parts to add to metadata (e.g. votes, history).",
+ "title": "Include"
+}Input schema / properties / max_chars / descriptionPrevious value: -"Most characters to return in this call, 1,000 to 200,000 (default 60,000). A longer document ends with a pointer to the next part."New value: +"Characters to return, 1,000 to 200,000."Input schema / properties / partAdded value: +{
+ "default": "document",
+ "description": "document (default), or one of the parts metadata.parts lists.",
+ "title": "Part",
+ "type": "string"
+}Input schema / properties / start / descriptionPrevious value: -"Where to start, as returned by the previous call's continuation pointer. 0 is the beginning."New value: +"Character offset to read from (the pointer at the end of a window gives it)."get_coverage3 fields changedInput schema / $defsAdded value: +{
+ "Filters": {
+ "additionalProperties": false,
+ "description": "Hard filters. Every field is optional; values come from the vocabularies.",
+ "properties": {
+ "action": {
+ "anyOf": [
+ {
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "description": "Stage of an action inside a meeting: reading, motion, vote, adopted, failed, public_comment, ...",
+ "title": "Action"
+ },
+ "body": {
+ "anyOf": [
+ {
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "description": "Issuing bodies by id, e.g. ga-supreme-court, ga-senate, ga-house-rules (describe_site lists them).",
+ "title": "Body"
+ },
+ "body_type": {
+ "anyOf": [
+ {
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "description": "Kinds of body: legislative_chamber, legislative_committee, court, board_of_education, governing_body, ...",
+ "title": "Body Type"
+ },
+ "branch": {
+ "anyOf": [
+ {
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "description": "Branches: legislative, executive, judicial.",
+ "title": "Branch"
+ },
+ "date_field": {
+ "anyOf": [
+ {
+ "enum": [
+ "date_primary",
+ "date_filed",
+ "date_met",
+ "date_adopted",
+ "date_effective"
+ ],
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "description": "Which date the range applies to; defaults to each type's own (filing date for opinions, meeting date for meetings).",
+ "title": "Date Field"
+ },
+ "date_from": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "description": "Earliest date: YYYY, YYYY-MM, or YYYY-MM-DD.",
+ "title": "Date From"
+ },
+ "date_to": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "description": "Latest date: YYYY, YYYY-MM, or YYYY-MM-DD.",
+ "title": "Date To"
+ },
+ "doc_type": {
+ "anyOf": [
+ {
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "description": "Document types, e.g. bill, opinion, code_section, constitution_provision, meeting_transcript, amendment.",
+ "title": "Doc Type"
+ },
+ "include_overlapping": {
+ "default": true,
+ "description": "With place: also bodies whose area overlaps it (Fulton and DeKalb for Atlanta).",
+ "title": "Include Overlapping",
+ "type": "boolean"
+ },
+ "level": {
+ "anyOf": [
+ {
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "description": "Levels of government: federal, state, county, municipal, consolidated, school_district, regional.",
+ "title": "Level"
+ },
+ "place": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "description": "A Georgia place in words or as an id (Atlanta, Cobb County, city:savannah). Matches the body's jurisdiction.",
+ "title": "Place"
+ },
+ "place_scope": {
+ "default": "either",
+ "description": "With place: documents issued for that place (jurisdiction), documents that mention it (mentions), or either (default).",
+ "enum": [
+ "either",
+ "jurisdiction",
+ "mentions"
+ ],
+ "title": "Place Scope",
+ "type": "string"
+ },
+ "session": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "description": "Legislative session slug, e.g. 2025-2026 or 2026-special.",
+ "title": "Session"
+ },
+ "status": {
+ "anyOf": [
+ {
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "description": "Status classes: pending, passed_one_chamber, passed_both, enacted, vetoed, failed, in_force, repealed, decided, held.",
+ "title": "Status"
+ }
+ },
+ "title": "Filters",
+ "type": "object"
+ }
+}Input schema / properties / filtersAdded value: +{
+ "anyOf": [
+ {
+ "$ref": "#/$defs/Filters"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "description": "Optional: narrow to document types, bodies, kinds of body, levels."
+}Output schema / (root)Previous value: -nullNew value: +{
+ "properties": {
+ "entries": {
+ "items": {
+ "additionalProperties": true,
+ "type": "object"
+ },
+ "title": "Entries",
+ "type": "array"
+ },
+ "not_held": {
+ "items": {
+ "type": "string"
+ },
+ "title": "Not Held",
+ "type": "array"
+ },
+ "not_held_yet": {
+ "items": {
+ "type": "string"
+ },
+ "title": "Not Held Yet",
+ "type": "array"
+ }
+ },
+ "required": [
+ "entries"
+ ],
+ "title": "CoverageOutput",
+ "type": "object"
+}meetings_for_billmeetings_get_transcriptmeetings_listmeetings_lookupmeetings_searchopinions_get_textopinions_listopinions_lookupopinions_searchsearch29 fields changedInput schema / $defsAdded value: +{
+ "Filters": {
+ "additionalProperties": false,
+ "description": "Hard filters. Every field is optional; values come from the vocabularies.",
+ "properties": {
+ "action": {
+ "anyOf": [
+ {
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "description": "Stage of an action inside a meeting: reading, motion, vote, adopted, failed, public_comment, ...",
+ "title": "Action"
+ },
+ "body": {
+ "anyOf": [
+ {
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "description": "Issuing bodies by id, e.g. ga-supreme-court, ga-senate, ga-house-rules (describe_site lists them).",
+ "title": "Body"
+ },
+ "body_type": {
+ "anyOf": [
+ {
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "description": "Kinds of body: legislative_chamber, legislative_committee, court, board_of_education, governing_body, ...",
+ "title": "Body Type"
+ },
+ "branch": {
+ "anyOf": [
+ {
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "description": "Branches: legislative, executive, judicial.",
+ "title": "Branch"
+ },
+ "date_field": {
+ "anyOf": [
+ {
+ "enum": [
+ "date_primary",
+ "date_filed",
+ "date_met",
+ "date_adopted",
+ "date_effective"
+ ],
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "description": "Which date the range applies to; defaults to each type's own (filing date for opinions, meeting date for meetings).",
+ "title": "Date Field"
+ },
+ "date_from": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "description": "Earliest date: YYYY, YYYY-MM, or YYYY-MM-DD.",
+ "title": "Date From"
+ },
+ "date_to": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "description": "Latest date: YYYY, YYYY-MM, or YYYY-MM-DD.",
+ "title": "Date To"
+ },
+ "doc_type": {
+ "anyOf": [
+ {
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "description": "Document types, e.g. bill, opinion, code_section, constitution_provision, meeting_transcript, amendment.",
+ "title": "Doc Type"
+ },
+ "include_overlapping": {
+ "default": true,
+ "description": "With place: also bodies whose area overlaps it (Fulton and DeKalb for Atlanta).",
+ "title": "Include Overlapping",
+ "type": "boolean"
+ },
+ "level": {
+ "anyOf": [
+ {
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "description": "Levels of government: federal, state, county, municipal, consolidated, school_district, regional.",
+ "title": "Level"
+ },
+ "place": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "description": "A Georgia place in words or as an id (Atlanta, Cobb County, city:savannah). Matches the body's jurisdiction.",
+ "title": "Place"
+ },
+ "place_scope": {
+ "default": "either",
+ "description": "With place: documents issued for that place (jurisdiction), documents that mention it (mentions), or either (default).",
+ "enum": [
+ "either",
+ "jurisdiction",
+ "mentions"
+ ],
+ "title": "Place Scope",
+ "type": "string"
+ },
+ "session": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "description": "Legislative session slug, e.g. 2025-2026 or 2026-special.",
+ "title": "Session"
+ },
+ "status": {
+ "anyOf": [
+ {
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "description": "Status classes: pending, passed_one_chamber, passed_both, enacted, vetoed, failed, in_force, repealed, decided, held.",
+ "title": "Status"
+ }
+ },
+ "title": "Filters",
+ "type": "object"
+ }
+}Input schema / properties / collectionRemoved value: -{
- "anyOf": [
- {
- "enum": [
- "code",
- "bills",
- "opinions",
- "meetings"
- ],
- "type": "string"
- },
- {
- "type": "null"
- }
- ],
- "default": null,
- "description": "Search one collection only: code (the Georgia Code and the two constitutions), bills, opinions, or meetings. Omit to search all four.",
- "title": "Collection"
-}Input schema / properties / cursorAdded value: +{
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "description": "The next_cursor of a previous call, for the next page.",
+ "title": "Cursor"
+}Input schema / properties / filtersAdded value: +{
+ "anyOf": [
+ {
+ "$ref": "#/$defs/Filters"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "description": "Optional hard filters (see describe_site for values)."
+}Input schema / properties / limitAdded value: +{
+ "anyOf": [
+ {
+ "maximum": 50,
+ "minimum": 1,
+ "type": "integer"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "description": "Results per page: 1 to 50 (default 10 documents; 25 in mode all).",
+ "title": "Limit"
+}Input schema / properties / linked_toAdded value: +{
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "description": "Only documents linked to this document id (a bill's meetings, a section's amending bills).",
+ "title": "Linked To"
+}Input schema / properties / modeAdded value: +{
+ "default": "best",
+ "description": "best: ranked and cut. all: every match found, by date, paged, with a total.",
+ "enum": [
+ "best",
+ "all"
+ ],
+ "title": "Mode",
+ "type": "string"
+}Input schema / properties / parentAdded value: +{
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "description": "Only documents inside this hierarchy node (code:t16, code:t16/c11, ga-const:art-i).",
+ "title": "Parent"
+}Input schema / properties / query / defaultAdded value: +""Input schema / properties / query / descriptionPrevious value: -"Words, a citation (44-7-34), a bill number (HB 136), or a docket (S23A0421). Search matches the words of the document."New value: +"A question or keywords, in plain language. Empty with filters: browse."Input schema / properties / relationsAdded value: +{
+ "anyOf": [
+ {
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "description": "With linked_to: relation types (discusses, amends, amendment_to, cites, ...).",
+ "title": "Relations"
+}Input schema / properties / sortAdded value: +{
+ "default": "relevance",
+ "description": "Result order.",
+ "enum": [
+ "relevance",
+ "newest",
+ "oldest",
+ "id"
+ ],
+ "title": "Sort",
+ "type": "string"
+}Input schema / properties / versionsAdded value: +{
+ "default": "current",
+ "description": "current (default) or all versions (how a bill changed).",
+ "enum": [
+ "current",
+ "all"
+ ],
+ "title": "Versions",
+ "type": "string"
+}Input schema / requiredRemoved value: -[
- "query"
-]Output schema / $defs / PassageAdded value: +{
+ "properties": {
+ "char_end": {
+ "anyOf": [
+ {
+ "type": "integer"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "title": "Char End"
+ },
+ "char_start": {
+ "anyOf": [
+ {
+ "type": "integer"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "title": "Char Start"
+ },
+ "cite": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "title": "Cite"
+ },
+ "link": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "title": "Link"
+ },
+ "locator": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "title": "Locator"
+ },
+ "role": {
+ "default": "evidence",
+ "title": "Role",
+ "type": "string"
+ },
+ "stage": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "title": "Stage"
+ },
+ "text": {
+ "title": "Text",
+ "type": "string"
+ },
+ "version_id": {
+ "title": "Version Id",
+ "type": "string"
+ }
+ },
+ "required": [
+ "text",
+ "version_id"
+ ],
+ "title": "Passage",
+ "type": "object"
+}Output schema / $defs / ResultAdded value: +{
+ "properties": {
+ "body": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "title": "Body"
+ },
+ "cite_as": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "title": "Cite As"
+ },
+ "date": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "title": "Date"
+ },
+ "date_field": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "title": "Date Field"
+ },
+ "doc_type": {
+ "title": "Doc Type",
+ "type": "string"
+ },
+ "exact": {
+ "default": false,
+ "title": "Exact",
+ "type": "boolean"
+ },
+ "id": {
+ "title": "Id",
+ "type": "string"
+ },
+ "level": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "title": "Level"
+ },
+ "occurrences": {
+ "default": 0,
+ "title": "Occurrences",
+ "type": "integer"
+ },
+ "passages": {
+ "items": {
+ "$ref": "#/$defs/Passage"
+ },
+ "title": "Passages",
+ "type": "array"
+ },
+ "score": {
+ "anyOf": [
+ {
+ "type": "number"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "title": "Score"
+ },
+ "status": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "title": "Status"
+ },
+ "summary": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "description": "Georgia Commons' AI-written summary: labeled, never source text.",
+ "title": "Summary"
+ },
+ "title": {
+ "title": "Title",
+ "type": "string"
+ },
+ "url": {
+ "title": "Url",
+ "type": "string"
+ }
+ },
+ "required": [
+ "id",
+ "title",
+ "url",
+ "doc_type"
+ ],
+ "title": "Result",
+ "type": "object"
+}Output schema / $defs / SearchResultRemoved value: -{
- "properties": {
- "id": {
- "title": "Id",
- "type": "string"
- },
- "title": {
- "title": "Title",
- "type": "string"
- },
- "url": {
- "title": "Url",
- "type": "string"
- }
- },
- "required": [
- "id",
- "title",
- "url"
- ],
- "title": "SearchResult",
- "type": "object"
-}Output schema / properties / confidenceAdded value: +{
+ "default": "medium",
+ "title": "Confidence",
+ "type": "string"
+}Output schema / properties / coverage_notesAdded value: +{
+ "items": {
+ "additionalProperties": true,
+ "type": "object"
+ },
+ "title": "Coverage Notes",
+ "type": "array"
+}Output schema / properties / documents_foundAdded value: +{
+ "anyOf": [
+ {
+ "type": "integer"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "title": "Documents Found"
+}Output schema / properties / facetsAdded value: +{
+ "additionalProperties": {
+ "items": {
+ "additionalProperties": true,
+ "type": "object"
+ },
+ "type": "array"
+ },
+ "title": "Facets",
+ "type": "object"
+}Output schema / properties / interpretationAdded value: +{
+ "additionalProperties": true,
+ "title": "Interpretation",
+ "type": "object"
+}Output schema / properties / next_cursorAdded value: +{
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "title": "Next Cursor"
+}Output schema / properties / queryAdded value: +{
+ "title": "Query",
+ "type": "string"
+}Output schema / properties / results / items / $refPrevious value: -"#/$defs/SearchResult"New value: +"#/$defs/Result"Output schema / properties / totalAdded value: +{
+ "anyOf": [
+ {
+ "type": "integer"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "title": "Total"
+}Output schema / properties / total_kindAdded value: +{
+ "default": "found",
+ "title": "Total Kind",
+ "type": "string"
+}Output schema / requiredPrevious value: -[
- "results"
-]New value: +[
+ "query",
+ "results"
+]Output schema / titlePrevious value: -"SearchResults"New value: +"SearchOutput"verify_quote17 fields changedInput schema / properties / id / descriptionPrevious value: -"The document's id, as search and fetch return it: code:44-7-34, bill:2025-2026/hb136, opinion:S26A0060, meeting:2026-02-05/house-rules."New value: +"The document id (or any written form of one)."Input schema / properties / id / maxLengthAdded value: +300Input schema / properties / quote / descriptionPrevious value: -"The quotation to check, at least 12 characters and at most 4,000."New value: +"The quotation to check, at least 12 characters."Input schema / properties / quote / minLengthPrevious value: -1New value: +12Input schema / properties / versionAdded value: +{
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "description": "A version id to check; default the current version, then earlier ones.",
+ "title": "Version"
+}Output schema / properties / canonical_urlAdded value: +{
+ "title": "Canonical Url",
+ "type": "string"
+}Output schema / properties / currentAdded value: +{
+ "anyOf": [
+ {
+ "type": "boolean"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "title": "Current"
+}Output schema / properties / foundAdded value: +{
+ "title": "Found",
+ "type": "boolean"
+}Output schema / properties / inAdded value: +{
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "title": "In"
+}Output schema / properties / md_urlAdded value: +{
+ "title": "Md Url",
+ "type": "string"
+}Output schema / properties / source_fieldRemoved value: -{
- "anyOf": [
- {
- "type": "string"
- },
- {
- "type": "null"
- }
- ],
- "title": "Source Field"
-}Output schema / properties / urlRemoved value: -{
- "title": "Url",
- "type": "string"
-}Output schema / properties / verifiedRemoved value: -{
- "title": "Verified",
- "type": "boolean"
-}Output schema / properties / version_idAdded value: +{
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "title": "Version Id"
+}Output schema / properties / version_labelAdded value: +{
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "title": "Version Label"
+}Output schema / requiredPrevious value: -[
- "id",
- "url",
- "verified",
- "occurrences",
- "source_field",
- "chars"
-]New value: +[
+ "id",
+ "found",
+ "occurrences",
+ "chars",
+ "canonical_url",
+ "md_url"
+]Output schema / titlePrevious value: -"VerifyResult"New value: +"VerifyOutput"bills_get_text8 fields changedInput schema / properties / bill / descriptionAdded value: +"The bill or resolution: HB 136, H.B. 136, House Bill 136, SR 5, 2025-2026/hb136, or a numeric id."Input schema / properties / bill / minLengthAdded value: +1Input schema / properties / max_chars / descriptionAdded value: +"Most characters to return in this call, 1,000 to 200,000 (default 60,000). A longer document ends with a pointer to the next part."Input schema / properties / max_chars / maximumAdded value: +200000Input schema / properties / max_chars / minimumAdded value: +1000Input schema / properties / session / descriptionAdded value: +"The session, named by its years or slug: 2025-2026 (the regular session) or 2026-special. Omit for the default the tool describes."Input schema / properties / start / descriptionAdded value: +"Where to start, as returned by the previous call's continuation pointer. 0 is the beginning."Input schema / properties / start / minimumAdded value: +0bills_list16 fields changedInput schema / properties / chamber / anyOfPrevious value: -[
- {
- "type": "string"
- },
- {
- "type": "null"
- }
-]New value: +[
+ {
+ "enum": [
+ "H",
+ "S"
+ ],
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+]Input schema / properties / chamber / descriptionAdded value: +"Chamber of origin: H (House) or S (Senate)."Input schema / properties / kind / anyOfPrevious value: -[
- {
- "type": "string"
- },
- {
- "type": "null"
- }
-]New value: +[
+ {
+ "enum": [
+ "hb",
+ "sb",
+ "hr",
+ "sr"
+ ],
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+]Input schema / properties / kind / descriptionAdded value: +"Kind of measure: hb (House bill), sb (Senate bill), hr (House resolution), or sr (Senate resolution)."Input schema / properties / limit / descriptionAdded value: +"How many entries per page, 1 to 40 (default 25)."Input schema / properties / limit / maximumAdded value: +40Input schema / properties / limit / minimumAdded value: +1Input schema / properties / q / anyOfPrevious value: -[
- {
- "type": "string"
- },
- {
- "type": "null"
- }
-]New value: +[
+ {
+ "maxLength": 500,
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+]Input schema / properties / q / descriptionAdded value: +"Words every listed bill must contain."Input schema / properties / session / descriptionAdded value: +"The session, named by its years or slug: 2025-2026 (the regular session) or 2026-special. Omit for the default the tool describes."Input schema / properties / start / descriptionAdded value: +"How many entries to skip, as returned by the previous call's continuation pointer. 0 is the first page."Input schema / properties / start / minimumAdded value: +0Input schema / properties / status / anyOfPrevious value: -[
- {
- "type": "integer"
- },
- {
- "type": "null"
- }
-]New value: +[
+ {
+ "maximum": 6,
+ "minimum": 1,
+ "type": "integer"
+ },
+ {
+ "type": "null"
+ }
+]Input schema / properties / status / descriptionAdded value: +"Status code: 1 Introduced, 2 Engrossed, 3 Enrolled, 4 Passed, 5 Vetoed, 6 Failed."Input schema / properties / subject / anyOfPrevious value: -[
- {
- "type": "string"
- },
- {
- "type": "null"
- }
-]New value: +[
+ {
+ "maxLength": 200,
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+]Input schema / properties / subject / descriptionAdded value: +"A caption subject, such as Education or Income tax: a search of titles, topic tags, and subjects."bills_lookup6 fields changedInput schema / properties / bill / descriptionAdded value: +"The bill or resolution: HB 136, H.B. 136, House Bill 136, SR 5, 2025-2026/hb136, or a numeric id."Input schema / properties / bill / minLengthAdded value: +1Input schema / properties / full / descriptionAdded value: +"Include the optional material the tool describes (for example votes and history, or the notes). Longer."Input schema / properties / max_charsAdded value: +{
+ "default": 60000,
+ "description": "Most characters to return in this call, 1,000 to 200,000 (default 60,000). A longer document ends with a pointer to the next part.",
+ "maximum": 200000,
+ "minimum": 1000,
+ "title": "Max Chars",
+ "type": "integer"
+}Input schema / properties / session / descriptionAdded value: +"The session, named by its years or slug: 2025-2026 (the regular session) or 2026-special. Omit for the default the tool describes."Input schema / properties / startAdded value: +{
+ "default": 0,
+ "description": "Where to start, as returned by the previous call's continuation pointer. 0 is the beginning.",
+ "minimum": 0,
+ "title": "Start",
+ "type": "integer"
+}bills_search8 fields changedInput schema / properties / in_headings / descriptionAdded value: +"Search only titles and headings instead of the full text."Input schema / properties / limit / descriptionAdded value: +"How many results to return, 1 to 40 (default 10)."Input schema / properties / limit / maximumAdded value: +40Input schema / properties / limit / minimumAdded value: +1Input schema / properties / query / descriptionAdded value: +"The words to search for, in the words the document itself would use."Input schema / properties / query / maxLengthAdded value: +2000Input schema / properties / query / minLengthAdded value: +1Input schema / properties / session / descriptionAdded value: +"The session, named by its years or slug: 2025-2026 (the regular session) or 2026-special. Omit for the default the tool describes."code_browse2 fields changedInput schema / properties / node / anyOfPrevious value: -[
- {
- "type": "string"
- },
- {
- "type": "null"
- }
-]New value: +[
+ {
+ "maxLength": 40,
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+]Input schema / properties / node / descriptionAdded value: +"A title ('36'), a title and chapter ('36-60'), or nothing for the list of titles."code_find_act3 fields changedInput schema / properties / name / descriptionAdded value: +"The law's short title as the statute states it: Joshua's Law, Georgia Lemonade Stand Act."Input schema / properties / name / maxLengthAdded value: +200Input schema / properties / name / minLengthAdded value: +1code_find_chapter3 fields changedInput schema / properties / words / descriptionAdded value: +"One or two words the Code would use as a heading: 'landlord and tenant', 'power of attorney'."Input schema / properties / words / maxLengthAdded value: +200Input schema / properties / words / minLengthAdded value: +1code_get_chapter15 fields changedInput schema / properties / chapter / descriptionAdded value: +"The chapter number within the title, as printed: 5, 11A."Input schema / properties / chapter / maxLengthAdded value: +10Input schema / properties / chapter / minLengthAdded value: +1Input schema / properties / max_chars / defaultPrevious value: -100000New value: +60000Input schema / properties / max_chars / descriptionAdded value: +"Most characters to return in this call, 1,000 to 200,000 (default 60,000). A longer document ends with a pointer to the next part."Input schema / properties / max_chars / maximumAdded value: +200000Input schema / properties / max_chars / minimumAdded value: +1000Input schema / properties / max_sections / descriptionAdded value: +"Most sections to return in this call, 1 to 200 (default 40)."Input schema / properties / max_sections / maximumAdded value: +200Input schema / properties / max_sections / minimumAdded value: +1Input schema / properties / start / descriptionAdded value: +"How many of the chapter's sections to skip, as the previous call's continuation pointer says. 0 is the first section."Input schema / properties / start / minimumAdded value: +0Input schema / properties / title / descriptionAdded value: +"The title number, 1 to 53 (Title 16 is Crimes and Offenses)."Input schema / properties / title / maximumAdded value: +53Input schema / properties / title / minimumAdded value: +1code_lookup_section9 fields changedInput schema / properties / citation / descriptionAdded value: +"One Code section in any written form: 44-7-34, O.C.G.A. § 44-7-34, Title 44, Chapter 7, Section 34, or with a subsection, 44-7-34(a)."Input schema / properties / citation / maxLengthAdded value: +200Input schema / properties / citation / minLengthAdded value: +1Input schema / properties / max_charsAdded value: +{
+ "default": 60000,
+ "description": "Most characters to return in this call, 1,000 to 200,000 (default 60,000). A longer document ends with a pointer to the next part.",
+ "maximum": 200000,
+ "minimum": 1000,
+ "title": "Max Chars",
+ "type": "integer"
+}Input schema / properties / startAdded value: +{
+ "default": 0,
+ "description": "Where to start, as returned by the previous call's continuation pointer. 0 is the beginning.",
+ "minimum": 0,
+ "title": "Start",
+ "type": "integer"
+}Input schema / properties / subsection / anyOfPrevious value: -[
- {
- "type": "string"
- },
- {
- "type": "null"
- }
-]New value: +[
+ {
+ "maxLength": 40,
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+]Input schema / properties / subsection / descriptionAdded value: +"One subsection to render alone, by its label: a, a-1, b."Input schema / properties / version / anyOfPrevious value: -[
- {
- "type": "string"
- },
- {
- "type": "null"
- }
-]New value: +[
+ {
+ "maxLength": 100,
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+]Input schema / properties / version / descriptionAdded value: +"Which printed version, by words of its effective-date qualifier, when a section is printed in more than one."code_lookup_sections3 fields changedInput schema / properties / citations / descriptionAdded value: +"A range ('44-7-30 through 44-7-35'), a list ('44-7-30, 44-7-31 and 44-7-34'), or a comma list of citations."Input schema / properties / citations / maxLengthAdded value: +2000Input schema / properties / citations / minLengthAdded value: +1code_search13 fields changedInput schema / properties / chapter / anyOfPrevious value: -[
- {
- "type": "string"
- },
- {
- "type": "null"
- }
-]New value: +[
+ {
+ "maxLength": 10,
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+]Input schema / properties / chapter / descriptionAdded value: +"Only sections in this chapter of `title` (5, 11A)."Input schema / properties / in_headings / descriptionAdded value: +"Search only titles and headings instead of the full text."Input schema / properties / limit / descriptionAdded value: +"How many results to return, 1 to 40 (default 10)."Input schema / properties / limit / maximumAdded value: +40Input schema / properties / limit / minimumAdded value: +1Input schema / properties / query / descriptionAdded value: +"The words to search for, in the words the document itself would use."Input schema / properties / query / maxLengthAdded value: +2000Input schema / properties / query / minLengthAdded value: +1Input schema / properties / scheme / descriptionAdded value: +"Which text to search: ocga (the Official Code of Georgia Annotated, the default), ga (the Constitution of the State of Georgia), or us (the Constitution of the United States)."Input schema / properties / scheme / enumAdded value: +[
+ "ocga",
+ "ga",
+ "us"
+]Input schema / properties / title / anyOfPrevious value: -[
- {
- "type": "integer"
- },
- {
- "type": "null"
- }
-]New value: +[
+ {
+ "maximum": 53,
+ "minimum": 1,
+ "type": "integer"
+ },
+ {
+ "type": "null"
+ }
+]Input schema / properties / title / descriptionAdded value: +"Only sections in this title of the Code (1 to 53)."constitution_browse4 fields changedInput schema / properties / node / anyOfPrevious value: -[
- {
- "type": "string"
- },
- {
- "type": "null"
- }
-]New value: +[
+ {
+ "maxLength": 20,
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+]Input schema / properties / node / descriptionAdded value: +"An article ('I', 'Art. IV') to list its provisions, or nothing for the outline."Input schema / properties / scheme / descriptionAdded value: +"Which constitution: ga (the Constitution of the State of Georgia) or us (the Constitution of the United States)."Input schema / properties / scheme / enumAdded value: +[
+ "ga",
+ "us"
+]constitution_lookup7 fields changedInput schema / properties / citation / descriptionAdded value: +"The provision: 'Art. I, Sec. I, Para. I' (Georgia), 'Art. I, Sec. 8' or 'Amend. XIV' (United States), 'Preamble', or a slug such as art-i-sec-i-para-i."Input schema / properties / citation / maxLengthAdded value: +200Input schema / properties / citation / minLengthAdded value: +1Input schema / properties / max_charsAdded value: +{
+ "default": 60000,
+ "description": "Most characters to return in this call, 1,000 to 200,000 (default 60,000). A longer document ends with a pointer to the next part.",
+ "maximum": 200000,
+ "minimum": 1000,
+ "title": "Max Chars",
+ "type": "integer"
+}Input schema / properties / scheme / descriptionAdded value: +"Which constitution: ga (the Constitution of the State of Georgia) or us (the Constitution of the United States)."Input schema / properties / scheme / enumAdded value: +[
+ "ga",
+ "us"
+]Input schema / properties / startAdded value: +{
+ "default": 0,
+ "description": "Where to start, as returned by the previous call's continuation pointer. 0 is the beginning.",
+ "minimum": 0,
+ "title": "Start",
+ "type": "integer"
+}fetch6 fields changedInput schema / properties / full / descriptionAdded value: +"Include the optional material the tool describes (for example votes and history, or the notes). Longer."Input schema / properties / id / descriptionAdded value: +"A document id from search: code:44-7-34, ga-const:art-i-sec-i-para-i, us-const:amend-xiv, bill:2025-2026/hb136, opinion:S26A0060, or meeting:2026-02-05/house-rules."Input schema / properties / id / minLengthAdded value: +1Input schema / properties / max_charsAdded value: +{
+ "default": 60000,
+ "description": "Most characters to return in this call, 1,000 to 200,000 (default 60,000). A longer document ends with a pointer to the next part.",
+ "maximum": 200000,
+ "minimum": 1000,
+ "title": "Max Chars",
+ "type": "integer"
+}Input schema / properties / startAdded value: +{
+ "default": 0,
+ "description": "Where to start, as returned by the previous call's continuation pointer. 0 is the beginning.",
+ "minimum": 0,
+ "title": "Start",
+ "type": "integer"
+}Output schema / (root)Previous value: -{
- "properties": {
- "id": {
- "title": "Id",
- "type": "string"
- },
- "metadata": {
- "additionalProperties": true,
- "title": "Metadata",
- "type": "object"
- },
- "text": {
- "title": "Text",
- "type": "string"
- },
- "title": {
- "title": "Title",
- "type": "string"
- },
- "url": {
- "title": "Url",
- "type": "string"
- }
- },
- "required": [
- "id",
- "title",
- "text",
- "url",
- "metadata"
- ],
- "title": "FetchResult",
- "type": "object"
-}New value: +nullmeetings_for_bill3 fields changedInput schema / properties / bill / descriptionAdded value: +"The bill: HB 629, SB 1, or 2025-2026/hb629."Input schema / properties / bill / minLengthAdded value: +1Input schema / properties / session / descriptionAdded value: +"The session, named by its years or slug: 2025-2026 (the regular session) or 2026-special. Omit for the default the tool describes."meetings_get_transcript7 fields changedInput schema / properties / max_chars / descriptionAdded value: +"Most characters to return in this call, 1,000 to 200,000 (default 60,000). A longer document ends with a pointer to the next part."Input schema / properties / max_chars / maximumAdded value: +200000Input schema / properties / max_chars / minimumAdded value: +1000Input schema / properties / meeting / descriptionAdded value: +"The meeting: its address (2026-02-05/house-rules), the General Assembly's video id or URL, or a body and a date (House Rules 2/5/2026)."Input schema / properties / meeting / minLengthAdded value: +1Input schema / properties / start / descriptionAdded value: +"Where to start, as returned by the previous call's continuation pointer. 0 is the beginning."Input schema / properties / start / minimumAdded value: +0meetings_list14 fields changedInput schema / properties / body / anyOfPrevious value: -[
- {
- "type": "string"
- },
- {
- "type": "null"
- }
-]New value: +[
+ {
+ "maxLength": 100,
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+]Input schema / properties / body / descriptionAdded value: +"One body by its slug (house-rules, senate-judiciary, house-floor) or its name."Input schema / properties / chamber / anyOfPrevious value: -[
- {
- "type": "string"
- },
- {
- "type": "null"
- }
-]New value: +[
+ {
+ "enum": [
+ "house",
+ "senate"
+ ],
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+]Input schema / properties / chamber / descriptionAdded value: +"Chamber: house or senate."Input schema / properties / date / descriptionAdded value: +"One day, written YYYY-MM-DD (2026-02-05)."Input schema / properties / kind / anyOfPrevious value: -[
- {
- "type": "string"
- },
- {
- "type": "null"
- }
-]New value: +[
+ {
+ "enum": [
+ "floor",
+ "committee",
+ "rules"
+ ],
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+]Input schema / properties / kind / descriptionAdded value: +"Kind of meeting: floor (a floor session), committee (a standing committee), or rules (the Rules Committee)."Input schema / properties / limit / descriptionAdded value: +"How many entries per page, 1 to 40 (default 25)."Input schema / properties / limit / maximumAdded value: +40Input schema / properties / limit / minimumAdded value: +1Input schema / properties / start / descriptionAdded value: +"How many entries to skip, as returned by the previous call's continuation pointer. 0 is the first page."Input schema / properties / start / minimumAdded value: +0Input schema / properties / year / anyOfPrevious value: -[
- {
- "type": "integer"
- },
- {
- "type": "null"
- }
-]New value: +[
+ {
+ "maximum": 2100,
+ "minimum": 2026,
+ "type": "integer"
+ },
+ {
+ "type": "null"
+ }
+]Input schema / properties / year / descriptionAdded value: +"One year (meetings are held from 2026 on)."meetings_lookup4 fields changedInput schema / properties / meeting / descriptionAdded value: +"The meeting: its address (2026-02-05/house-rules), the General Assembly's video id or URL, or a body and a date (House Rules 2/5/2026)."Input schema / properties / meeting / minLengthAdded value: +1Input schema / properties / start / anyOfPrevious value: -[
- {
- "type": "integer"
- },
- {
- "type": "null"
- }
-]New value: +[
+ {
+ "minimum": 0,
+ "type": "integer"
+ },
+ {
+ "type": "null"
+ }
+]Input schema / properties / start / descriptionAdded value: +"A character offset into the transcript: returns that part of the transcript alone instead of the meeting with its summaries."meetings_search13 fields changedInput schema / properties / body / anyOfPrevious value: -[
- {
- "type": "string"
- },
- {
- "type": "null"
- }
-]New value: +[
+ {
+ "maxLength": 100,
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+]Input schema / properties / body / descriptionAdded value: +"Only this body, by its slug (house-rules, senate-judiciary)."Input schema / properties / chamber / anyOfPrevious value: -[
- {
- "type": "string"
- },
- {
- "type": "null"
- }
-]New value: +[
+ {
+ "enum": [
+ "house",
+ "senate"
+ ],
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+]Input schema / properties / chamber / descriptionAdded value: +"Chamber: house or senate."Input schema / properties / in_headings / descriptionAdded value: +"Search only titles and headings instead of the full text."Input schema / properties / kind / anyOfPrevious value: -[
- {
- "type": "string"
- },
- {
- "type": "null"
- }
-]New value: +[
+ {
+ "enum": [
+ "floor",
+ "committee",
+ "rules"
+ ],
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+]Input schema / properties / kind / descriptionAdded value: +"Kind of meeting: floor (a floor session), committee (a standing committee), or rules (the Rules Committee)."Input schema / properties / limit / descriptionAdded value: +"How many results to return, 1 to 40 (default 10)."Input schema / properties / limit / maximumAdded value: +40Input schema / properties / limit / minimumAdded value: +1Input schema / properties / query / descriptionAdded value: +"The words to search for, in the words the document itself would use."Input schema / properties / query / maxLengthAdded value: +2000Input schema / properties / query / minLengthAdded value: +1opinions_get_text7 fields changedInput schema / properties / max_chars / descriptionAdded value: +"Most characters to return in this call, 1,000 to 200,000 (default 60,000). A longer document ends with a pointer to the next part."Input schema / properties / max_chars / maximumAdded value: +200000Input schema / properties / max_chars / minimumAdded value: +1000Input schema / properties / opinion / descriptionAdded value: +"The opinion: a docket number (S23A0421), a reporter citation (317 Ga. 528), a record id, or a case name."Input schema / properties / opinion / minLengthAdded value: +1Input schema / properties / start / descriptionAdded value: +"Where to start, as returned by the previous call's continuation pointer. 0 is the beginning."Input schema / properties / start / minimumAdded value: +0opinions_list11 fields changedInput schema / properties / case_type / anyOfPrevious value: -[
- {
- "type": "string"
- },
- {
- "type": "null"
- }
-]New value: +[
+ {
+ "enum": [
+ "criminal appeal",
+ "civil",
+ "bar discipline",
+ "habeas",
+ "certified question",
+ "election",
+ "other"
+ ],
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+]Input schema / properties / case_type / descriptionAdded value: +"Kind of case: criminal appeal, civil, bar discipline, habeas, certified question, election, or other."Input schema / properties / limit / descriptionAdded value: +"How many entries per page, 1 to 40 (default 25)."Input schema / properties / limit / maximumAdded value: +40Input schema / properties / limit / minimumAdded value: +1Input schema / properties / q / anyOfPrevious value: -[
- {
- "type": "string"
- },
- {
- "type": "null"
- }
-]New value: +[
+ {
+ "maxLength": 500,
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+]Input schema / properties / q / descriptionAdded value: +"Words every listed opinion must contain."Input schema / properties / start / descriptionAdded value: +"How many entries to skip, as returned by the previous call's continuation pointer. 0 is the first page."Input schema / properties / start / minimumAdded value: +0Input schema / properties / year / anyOfPrevious value: -[
- {
- "type": "integer"
- },
- {
- "type": "null"
- }
-]New value: +[
+ {
+ "maximum": 2100,
+ "minimum": 2000,
+ "type": "integer"
+ },
+ {
+ "type": "null"
+ }
+]Input schema / properties / year / descriptionAdded value: +"The year filed (opinions are held from 2020 on). Omit for the newest year."opinions_lookup5 fields changedInput schema / properties / full / descriptionAdded value: +"Include the optional material the tool describes (for example votes and history, or the notes). Longer."Input schema / properties / max_charsAdded value: +{
+ "default": 60000,
+ "description": "Most characters to return in this call, 1,000 to 200,000 (default 60,000). A longer document ends with a pointer to the next part.",
+ "maximum": 200000,
+ "minimum": 1000,
+ "title": "Max Chars",
+ "type": "integer"
+}Input schema / properties / opinion / descriptionAdded value: +"The opinion: a docket number (S23A0421), a reporter citation (317 Ga. 528), a record id, or a case name."Input schema / properties / opinion / minLengthAdded value: +1Input schema / properties / startAdded value: +{
+ "default": 0,
+ "description": "Where to start, as returned by the previous call's continuation pointer. 0 is the beginning.",
+ "minimum": 0,
+ "title": "Start",
+ "type": "integer"
+}opinions_search11 fields changedInput schema / properties / case_type / anyOfPrevious value: -[
- {
- "type": "string"
- },
- {
- "type": "null"
- }
-]New value: +[
+ {
+ "enum": [
+ "criminal appeal",
+ "civil",
+ "bar discipline",
+ "habeas",
+ "certified question",
+ "election",
+ "other"
+ ],
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+]Input schema / properties / case_type / descriptionAdded value: +"Kind of case: criminal appeal, civil, bar discipline, habeas, certified question, election, or other."Input schema / properties / in_headings / descriptionAdded value: +"Search only titles and headings instead of the full text."Input schema / properties / limit / descriptionAdded value: +"How many results to return, 1 to 40 (default 10)."Input schema / properties / limit / maximumAdded value: +40Input schema / properties / limit / minimumAdded value: +1Input schema / properties / query / descriptionAdded value: +"The words to search for, in the words the document itself would use."Input schema / properties / query / maxLengthAdded value: +2000Input schema / properties / query / minLengthAdded value: +1Input schema / properties / year / anyOfPrevious value: -[
- {
- "type": "integer"
- },
- {
- "type": "null"
- }
-]New value: +[
+ {
+ "maximum": 2100,
+ "minimum": 2000,
+ "type": "integer"
+ },
+ {
+ "type": "null"
+ }
+]Input schema / properties / year / descriptionAdded value: +"Only opinions filed in this year."search4 fields changedInput schema / properties / collection / anyOfPrevious value: -[
- {
- "type": "string"
- },
- {
- "type": "null"
- }
-]New value: +[
+ {
+ "enum": [
+ "code",
+ "bills",
+ "opinions",
+ "meetings"
+ ],
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+]Input schema / properties / collection / descriptionAdded value: +"Search one collection only: code (the Georgia Code and the two constitutions), bills, opinions, or meetings. Omit to search all four."Input schema / properties / query / descriptionAdded value: +"Words, a citation (44-7-34), a bill number (HB 136), or a docket (S23A0421). Search matches the words of the document."Input schema / properties / query / maxLengthAdded value: +2000verify_quote5 fields changedInput schema / properties / id / descriptionAdded value: +"The document's id, as search and fetch return it: code:44-7-34, bill:2025-2026/hb136, opinion:S26A0060, meeting:2026-02-05/house-rules."Input schema / properties / id / minLengthAdded value: +1Input schema / properties / quote / descriptionAdded value: +"The quotation to check, at least 12 characters and at most 4,000."Input schema / properties / quote / maxLengthAdded value: +4000Input schema / properties / quote / minLengthAdded value: +1meetings_for_billmeetings_get_transcriptmeetings_listmeetings_lookupmeetings_searchOfficial Code of Georgia Annotated (O.C.G.A.) — Georgia state statutes by citation, topic search…
U.S. bills, roll-call votes, legislators and 2026 elections for all 50 states, D.C. and Congress.
Georgia K-12 standards, Milestones blueprints, and achievement levels for educators. Independent.
Read-only public data on Georgia's prisons: population, facilities, deaths, contraband, statutes.
Add one secure layer between your agents and this server.