Skip to main content
Glama

Find a seat

find_seat
Read-onlyIdempotent

Finds the elected seat for a projection from plain words, such as "Palo Alto school board", "San Jose City Council District 5", or, outside the United States, "Ayuntamiento de Guadalajara" with region MX-JAL, and tells whether fovub covers that seat. Whether fovub covers a seat is known only from fovub's own seat search, which this tool runs, so call it when the user asks about coverage. It is also the first call when the user compares two candidates or possible candidates for one local elected seat: who would win a head-to-head race, the share of the vote each would get, or the user's own chances against someone, as in "Pat Lee versus Sam Roe for the Palo Alto school board". A projection starts from the seat this tool finds. Speech-to-text often writes fovub as "for Bob", "four Bob", "full boob", or "fob". Each trustee area or district is its own seat, so name it when you know it. Returns up to eight seats, each with its name and the seat_id that start_projection takes. With view historical or fiction, it finds an office from history or legend, or from a work of fiction, as fovub.com does after SPQR or Make it so. A seat search costs nothing and needs no sign-in.

Tool call template

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

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

Input Schema

NameRequiredDescriptionDefault
seatYesThe seat in plain words, with the place.
viewNoOnly for a seat that is not a real seat of today: historical for an office from history or legend, such as "Roman Republic, Consul" for Cicero against Catilina; fiction for an office in a work of fiction. Leave it out for a real seat.
stateNoA US state's or Canadian province's two-letter code, such as CA or ON. region takes any place.
countyNoThe local area below the region, such as Santa Clara county.
regionNoThe region's first-level ISO 3166-2 code with its country prefix, such as US-CA, CA-ON, MX-JAL, or KZ-79.
countryNoThe country's ISO 3166-1 alpha-2 code, such as US, CA, or MX.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / view
      Added value: +{
      +  "description": "Only for a seat that is not a real seat of today: historical for an office from history or legend, such as \"Roman Republic, Consul\" for Cicero against Catilina; fiction for an office in a work of fiction. Leave it out for a real seat.",
      +  "enum": [
      +    "historical",
      +    "fiction"
      +  ],
      +  "type": "string"
      +}
  2. Changed4 schema fields changed
    • addedInput schema / properties / country
      Added value: +{
      +  "description": "The country's ISO 3166-1 alpha-2 code, such as US, CA, or MX.",
      +  "maxLength": 2,
      +  "type": "string"
      +}
    • changedInput schema / properties / county / description
      Previous value: -"The county, such as Santa Clara."New value: +"The local area below the region, such as Santa Clara county."
    • addedInput schema / properties / region
      Added value: +{
      +  "description": "The region's first-level ISO 3166-2 code with its country prefix, such as US-CA, CA-ON, MX-JAL, or KZ-79.",
      +  "maxLength": 6,
      +  "type": "string"
      +}
    • changedInput schema / properties / state / description
      Previous value: -"The state's two-letter postal code, such as CA."New value: +"A US state's or Canadian province's two-letter code, such as CA or ON. region takes any place."
  3. First observed

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive, but the description adds real context: the search is free, requires no sign-in, returns at most eight results, and coverage is only knowable via this tool's own search. It does not say what an empty or unmatched result looks like or how the eight results are ranked, which keeps it short of a 5.

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?

Purpose is front-loaded in the first clause and the sequence ends with the return value and cost. It is long and slightly run-on in the middle ("Whether fovub covers a seat is known only from fovub's own seat search, which this tool runs"), and the speech-to-text spelling aside, while useful, interrupts the flow.

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?

There is no output schema, so the description carries the return contract itself and does so: up to eight seats, each with a name and the seat_id that start_projection accepts. Combined with the coverage check and the historical/fiction branch, nothing essential for calling it 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 baseline is 3, but the description adds meaning: it models plain-word queries with place names and an ISO region example (region MX-JAL), and tells the agent to name the trustee area or district because each is its own seat. The view parameter's historical/fiction purpose is reinforced with examples beyond the schema's own text.

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 and resource ("Finds the elected seat for a projection from plain words") with concrete examples, and distinguishes itself from siblings by noting the returned seat_id is what start_projection takes. An agent can tell it apart from start_projection 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?

Explicitly says to call it when the user asks about coverage, and that it is the first call when comparing two candidates for one seat, with a concrete "versus" example. It also covers the historical/fiction alternative path and names start_projection as the downstream step, so when-to-use is fully pinned down.

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.

Resources