OpenPublica

Search meetings

search_meetings_semantic

Read-only

Search OpenPublica meeting summaries by meaning, exact terms, or both.

The best default tool for "what has been said/decided about X" questions.
Results carry a `relevance_score` (semantic, 0-1) and/or `keyword_score` (BM25)
plus `highlights`, so you can triage matches by confidence. If the response sets
`degraded_to_vector`, the keyword index was unavailable and results are
semantic-only — do NOT treat them as exact-term matches. Narrow with
`category_tag`/`topic` (get valid values from `discover_meeting_vocabulary`), a
date range, or one or more governments. Returns a summary preview; call
`get_meeting` with a returned `meeting_id` for the full summary or transcript.

Input Schema

TableJSON Schema

Name	Required	Description
`limit`	No	Max meetings to return (1-25).
`query`	Yes	What to search for in plain language, e.g. 'short-term rental regulations' or 'police budget overtime'.
`topic`	No	Optional topic filter — a topic name from discover_meeting_vocabulary, e.g. 'Affordable Housing'. Restricts to meetings that discussed it.
`end_date`	No	Optional latest meeting date, MM-DD-YYYY.
`min_score`	No	Optional semantic relevance floor 0-1 (default 0.4). Raise to return only strong matches; lower to widen recall. Applies to semantic matching only — keyword (BM25) hits are not filtered by it.
`match_type`	No	How to match: 'semantic' (default, by meaning — best for concepts/paraphrases), 'keyword' (exact terms — best for names, ordinance numbers, quoted phrases), or 'hybrid' (both, rank-fused). Use keyword/hybrid when the query has a literal string an embedding might miss.
`start_date`	No	Optional earliest meeting date, MM-DD-YYYY.
`category_tag`	No	Optional meeting-type filter — an opaque category_tag from discover_meeting_vocabulary (not a guessable slug).
`government_id`	No	Optional account_id (from find_local_governments) to restrict the search to one government.
`government_ids`	No	Optional list of account_ids to search across several governments at once (e.g. to compare cities). Overrides government_id.

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

TDQS

A4.7/5.0

Behavior5/5

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

Beyond the readOnly/openWorld annotations, the description discloses important runtime behavior: results include relevance_score and keyword_score, and the degraded_to_vector flag means hits are semantic-only and must not be treated as exact-term matches. It also reveals that the response is a summary preview, not the full meeting.

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

Conciseness5/5

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

Three front-loaded sentences with no filler: purpose, scoring/confidence caveat, narrowing options, and follow-up action. Every sentence earns its place and the most important guidance appears first.

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

Completeness5/5

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

With a rich output schema and readOnly/openWorld annotations already present, the description covers the remaining decision-relevant context: how to filter, how to interpret degraded results, and how to get full text. Nothing an agent needs in order to call this tool correctly is missing.

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

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the schema carries most parameter meaning; the description adds value by framing how to narrow results (category_tag/topic from discover_meeting_vocabulary, date range, one or more governments) and warns about degraded keyword behavior. It does not add much beyond the schema for individual parameters like min_score and match_type, but the schema already documents those clearly.

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

Purpose5/5

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

The first sentence names a specific verb and resource — 'Search OpenPublica meeting summaries' — and immediately disambiguates the search modes ('by meaning, exact terms, or both'). Calling itself 'the best default tool' for topic questions distinguishes it from siblings without opening schemas.

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

Usage Guidelines4/5

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

It gives explicit default usage ('best default tool for ... X questions'), tells the agent where to get filter values (discover_meeting_vocabulary), and routes follow-up lookups to get_meeting. It does not explicitly state when to choose search_meeting_transcript or search_documents over this tool, so it stops short of full when-not guidance.

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

All OpenPublica tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.4/5.0

Disambiguation5/5

Each tool targets a clear, distinct operation: government discovery, meeting search, transcript search, document listing, and document reading are all cleanly separated. The three find_governments tools overlap in purpose but are differentiated by input type (name, ZIP, coordinates), and the descriptions explicitly call out when to prefer one over another.

Naming Consistency5/5

Tool names follow a consistent and predictable verb_noun pattern: find_governments_by_*, get_*, list_*, search_*, read_*, and discover_*. The qualifiers are descriptive and parallel, making the intended action and resource obvious from the name alone.

Tool Count5/5

At 15 tools, the set is at the upper end of the ideal range but every tool earns its place by covering a distinct capability across two related domains: meetings and government documents. There is no filler or redundancy; the count feels well-scoped for the server's stated purpose.

Completeness5/5

For a read-only public-records service, the surface is remarkably complete: government resolution by name/ZIP/coordinates, coverage, stats, meeting discovery/search/retrieval, transcript-level search, and document listing/search/reading all have dedicated tools. There are no obvious dead ends—every search path leads to a retrieval tool that can produce citable quotes, pages, or full transcripts.

Resources

Need Help?