Skip to main content
Glama
DogPolicies MCP Server

DogPolicies MCP Server

by xultrax-web

Follow rule changes in a feed

dogpolicies_subscribe_changes
Read-onlyIdempotent

Get Atom and JSON feed links for dog rule changes by place, area, or highway stretch, plus 90-day change counts, to follow updates in any feed reader.

Instructions

Can you tell me if the dog rules change at Carmel Beach before our trip? Can I follow changes near Lake Tahoe, or along I-5? For hearing about changes later, without asking again: it answers with a feed link (Atom and JSON Feed) for one place, a town, county, area or neighborhood with a radius, or a highway's stops, which any feed reader can follow. It computes the links and counts only; it signs nobody up, stores nothing and sends no email. Inputs: one of place (a place id from any answer, e.g. "carmel-beach"), near (a town, county, area, region or neighborhood, e.g. "Lake Tahoe", "Monterey", "Van Nuys") with radius_miles, or route (i-5, us-101, highway-1, i-15, i-80, us-50, or a Nevada route ending in -nevada) with from_mile and to_mile. Returns atom_url and json_url, how many verification events, rule changes and corrections the scope had in the last 90 days, the page for the scope, and share_text: a sentence with the link, written for the traveler. An unknown name is an answer with did_you_mean.

Examples:

  • "Tell me if the rules change at Carmel Beach" -> place="carmel-beach"

  • "Can I get alerts for dog rule changes around Lake Tahoe?" -> near="Lake Tahoe"

  • "Follow changes on the Grapevine stretch of I-5" -> route="i-5", from_mile=170, to_mile=222

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

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

Input Schema

NameRequiredDescriptionDefault
nearNoA city, county, area, region or neighborhood in California or Nevada, e.g. "Lake Tahoe", "Monterey", "Washoe County, NV", "Van Nuys"
placeNoOne place by its id from any answer, e.g. "carmel-beach" (a close name is matched and labeled)
routeNoA highway, e.g. "i-5", "us-101", "highway-1", "i-80-nevada"
to_mileNoWith route: end of the stretch, in route miles
from_mileNoWith route: start of the stretch, in route miles
radius_milesNoWith near: miles around the town (an area or region is its own boundary; the radius is ignored)
response_formatNo'markdown' for readable text, 'json' for structured datamarkdown

Output Schema

NameRequiredDescriptionDefault
codeNoWith an outcome other than ok: not_found, invalid, unavailable
nextNoCalls that would answer the question, in words
as_ofYesDate the data was built (YYYY-MM-DD)
scopeYesWhat the feed follows: place, near or route, its id and label
licenseYes
messageNoWhat happened, in a sentence
nearestNoWhen nothing is inside the radius: the nearest places in the data, with distance_miles
outcomeNoAbsent or ok: a normal answer. no_match: nothing in the data matches, see did_you_mean, nearest and next. bad_input: the arguments cannot be used as given, see next. partial: some of the ids were found, see missing. unavailable: a live source could not be read. None of these is an error.
acceptedNoWith bad_input: each argument that could not be read, with the values it accepts
atom_urlYesThe Atom 1.0 feed for the scope
json_urlYesThe JSON Feed 1.1 feed for the scope
page_urlYesThe page for the scope (the place's record or the road-trip guide), when there is one
share_textYesA sentence with the feed link, written for the traveler
did_you_meanNoClose matches to what was asked for: towns, places, slugs or brands, best first
last_90_daysYesActivity in the scope over the last 90 days: verification events (re-checks included), rule changes (events whose outcome is changed, plus the rule-change log) and correction tickets (the hosted server only)
resolved_fromNoSet when a word was read as the value the tool uses: hotel as lodging, NB as north. Each key is the argument; asked is what was sent, used what it was read as
attribution_urlYes
attribution_textYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.5.0

TDQS

A4.2/5.0
Behavior5/5

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

Beyond the readOnly/idempotent/no-destructive annotations, the description discloses that it computes links and counts only, stores nothing, sends no email, and signs nobody up. It also describes the return payload (atom_url, json_url, counts for the last 90 days, page, share_text) and the did_you_mean fallback for unknown names, giving rich behavioral context.

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

Conciseness3/5

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

The content is front-loaded and informative, but the opening user-question framing ('Can you tell me if...') duplicates the Examples section and adds chattiness. The long middle sentence packs several ideas; it is dense but not maximally economical for an agent-facing definition.

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?

Given seven optional parameters, three input modes, and an output schema, the description covers the mode selection, no-side-effect behavior, return fields, and error handling. An agent has everything needed to invoke it correctly without guessing.

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 each parameter is already documented. The description adds meaning by explaining the mutually exclusive modes: one of place, near with radius_miles, or route with from_mile/to_mile, and notes that place ids come 'from any answer.' This grouping is not expressible in the flat schema and helps the agent choose parameters correctly.

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

Purpose4/5

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

States a specific action and output: 'answers with a feed link (Atom and JSON Feed)' for a place, near-area, or highway stretch. It distinguishes itself from one-off queries by framing this as 'For hearing about changes later, without asking again,' though it doesn't name sibling tools like dogpolicies_changes_near explicitly.

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?

Provides a clear use case: following changes later without re-asking, as opposed to immediate queries. It also clarifies what it is not ('signs nobody up, stores nothing and sends no email') and enumerates the three input modes. It does not explicitly point to the sibling tool to use for an immediate one-time answer, leaving that inference to the agent.

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