Skip to main content
Glama

Ca Ota Search

ca_ota_search
Read-onlyIdempotent

Find California Office of Tax Appeals (OTA) opinions by statute citation or topic keyword (e.g. "residency", "innocent spouse", "17014", "17951-4", "generative AI") -- returns citation, title, date, tax category (Franchise/Income vs Business Tax), precedential status, and OTA's own one-line issue/statute tag, most recent first with an exact phrase match ranked above a looser match. Matches every word of query (any order), with a small bidirectional synonym table for OTA's own shorthand (e.g. "GenAI" <-> "generative AI" <-> "AI" <-> "artificial intelligence"). Use year for "opinions from 2026" rather than putting the year in query text -- it almost never appears inside an opinion's title or Issues tag. PARTIAL: this searches opinion titles and OTA's published "Issues" tag only, not full opinion text (OTA publishes no full-text search). For full text and all cited provisions of a specific opinion, use ca_ota_opinion_lookup. Sourced from ota.ca.gov's own opinion listing pages.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "query": "residency"
    },
    "name": "ca_ota_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
yearNoOptional filter: only opinions issued in this calendar year, e.g. 2026. Prefer this over putting the year inside `query` -- OTA's own title/Issues tag almost never repeats the year.
limitNoMax opinions to return, default 25, max 100.
queryNoA topic keyword (e.g. "residency", "penalties", "innocent spouse", "generative AI") or a statute citation/number (e.g. "17014" or "R&TC 19045"). May be omitted if you only need `year`/`category`/`precedential_only` filters. A bare year inside this text (e.g. "2026") is treated as a `year` filter, not as text to match.
categoryNoOptional filter: "fit" (Franchise and Income Tax, FTB-administered) or "bt" (Business Tax, CDTFA-administered: sales/use, excise, etc).
precedential_onlyNoIf true, only return opinions OTA has designated Precedential (binding on future OTA panels). Default false (returns both).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • changedInput schema / examples
      Previous value: -[
      -  {
      -    "query": "residency"
      -  }
      -]New value: +[
      +  {
      +    "query": "residency"
      +  },
      +  {
      +    "query": "generative AI"
      +  },
      +  {
      +    "precedential_only": true,
      +    "year": 2026
      +  }
      +]
    • changedInput schema / properties / query / description
      Previous value: -"A topic keyword (e.g. \"residency\", \"penalties\", \"innocent spouse\") or a statute citation/number (e.g. \"17014\" or \"R&TC 19045\")."New value: +"A topic keyword (e.g. \"residency\", \"penalties\", \"innocent spouse\", \"generative AI\") or a statute citation/number (e.g. \"17014\" or \"R&TC 19045\"). May be omitted if you only need `year`/`category`/`precedential_only` filters. A bare year inside this text (e.g. \"2026\") is treated as a `year` filter, not as text to match."
    • addedInput schema / properties / year
      Added value: +{
      +  "description": "Optional filter: only opinions issued in this calendar year, e.g. 2026. Prefer this over putting the year inside `query` -- OTA's own title/Issues tag almost never repeats the year.",
      +  "type": "number"
      +}
    • changedInput schema / required
      Previous value: -[
      -  "query"
      -]New value: +[]
  2. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), but the description adds substantial behavior: coverage is limited to titles and OTA's Issues tag, exact-phrase matches rank above looser ones, a bidirectional synonym table is applied, and all query words must match in any order. It also names the data source (ota.ca.gov).

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

Conciseness4/5

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

Front-loaded with purpose and limits, and every sentence carries information. It is dense and parenthetical-heavy, making it slightly harder to scan, but there is little genuine waste.

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?

Even without an output schema, the description enumerates the returned fields (citation, title, date, tax category, precedential status, OTA issue/statute tag) and the ordering. Coverage limits and the sibling alternative complete the picture for a search tool.

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 baseline is 3, but the description adds meaning beyond the schema: it explains synonym expansion for `query` and reinforces the query-vs-year interaction. It does not add much for `limit`, `category`, or `precedential_only`, which the schema already documents.

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?

States a specific verb (Find) and resource (California Office of Tax Appeals opinions), plus the exact retrieval keys (statute citation or topic keyword). It explicitly distinguishes itself from the sibling ca_ota_opinion_lookup, so an agent can route correctly without opening either schema.

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

Usage Guidelines5/5

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

Gives explicit when-to-use guidance for `year` versus embedding a year in `query`, and names the alternative for full-text needs (ca_ota_opinion_lookup). The PARTIAL note clarifies when this tool will not suffice.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.