Skip to main content
Glama

Casatoo

Search Casatoo locations

casatoo_search_locations
Read-onlyIdempotent

Step 1 of every location-based operation. Find candidate Casatoo location IDs by place name, slug, district, municipality, parish, or neighborhood. Inspect selection_state and location_type; ask the user when selection_required and never invent an ID.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNo
queryYesHuman place text used only to discover candidate Casatoo location IDs. Common unambiguous English aliases such as Lisbon are accepted.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryYes
locationsYes
selection_stateYes
normalized_queryYes
query_interpretationYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed27 schema fields changed
    • addedInput schema / $defs
      Added value: +{
      +  "LocationQuery": {
      +    "maxLength": 120,
      +    "minLength": 1,
      +    "type": "string"
      +  }
      +}
    • addedInput schema / additionalProperties
      Added value: +false
    • addedInput schema / properties / query / $ref
      Added value: +"#/$defs/LocationQuery"
    • addedInput schema / properties / query / description
      Added value: +"Human place text used only to discover candidate Casatoo location IDs. Common unambiguous English aliases such as Lisbon are accepted."
    • removedInput schema / properties / query / maxLength
      Removed value: -120
    • removedInput schema / properties / query / minLength
      Removed value: -1
    • removedInput schema / properties / query / title
      Removed value: -"Query"
    • removedInput schema / properties / query / type
      Removed value: -"string"
    • addedOutput schema / $defs / AgentLocationType
      Added value: +{
      +  "enum": [
      +    "DISTRICT",
      +    "MUNICIPALITY",
      +    "PARISH",
      +    "NEIGHBORHOOD"
      +  ],
      +  "title": "AgentLocationType",
      +  "type": "string"
      +}
    • addedOutput schema / $defs / LocationId
      Added value: +{
      +  "minimum": 1,
      +  "type": "integer"
      +}
    • addedOutput schema / $defs / LocationQueryInterpretation
      Added value: +{
      +  "enum": [
      +    "literal",
      +    "alias"
      +  ],
      +  "title": "LocationQueryInterpretation",
      +  "type": "string"
      +}
    • addedOutput schema / $defs / LocationSearchResult / properties / id / $ref
      Added value: +"#/$defs/LocationId"
    • addedOutput schema / $defs / LocationSearchResult / properties / id / description
      Added value: +"Exact location ID to pass unchanged to listing search and search-link tools."
    • removedOutput schema / $defs / LocationSearchResult / properties / id / title
      Removed value: -"Id"
    • removedOutput schema / $defs / LocationSearchResult / properties / id / type
      Removed value: -"integer"
    • addedOutput schema / $defs / LocationSearchResult / properties / location_type / $ref
      Added value: +"#/$defs/AgentLocationType"
    • addedOutput schema / $defs / LocationSearchResult / properties / location_type / description
      Added value: +"Administrative level: DISTRICT, MUNICIPALITY, PARISH, or NEIGHBORHOOD."
    • removedOutput schema / $defs / LocationSearchResult / properties / location_type / title
      Removed value: -"Location Type"
    • removedOutput schema / $defs / LocationSearchResult / properties / location_type / type
      Removed value: -"string"
    • changedOutput schema / $defs / LocationSearchResult / properties / parent_id / anyOf
      Previous value: -[
      -  {
      -    "type": "integer"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]New value: +[
      +  {
      +    "$ref": "#/$defs/LocationId"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • removedOutput schema / $defs / LocationSearchResult / properties / parent_id / title
      Removed value: -"Parent Id"
    • addedOutput schema / $defs / LocationSelectionState
      Added value: +{
      +  "enum": [
      +    "no_candidates",
      +    "single_candidate",
      +    "selection_required"
      +  ],
      +  "title": "LocationSelectionState",
      +  "type": "string"
      +}
    • addedOutput schema / properties / normalized_query
      Added value: +{
      +  "title": "Normalized Query",
      +  "type": "string"
      +}
    • addedOutput schema / properties / query
      Added value: +{
      +  "title": "Query",
      +  "type": "string"
      +}
    • addedOutput schema / properties / query_interpretation
      Added value: +{
      +  "$ref": "#/$defs/LocationQueryInterpretation"
      +}
    • addedOutput schema / properties / selection_state
      Added value: +{
      +  "$ref": "#/$defs/LocationSelectionState"
      +}
    • changedOutput schema / required
      Previous value: -[
      -  "locations"
      -]New value: +[
      +  "query",
      +  "normalized_query",
      +  "query_interpretation",
      +  "selection_state",
      +  "locations"
      +]
  2. First observed

TDQS

A4.2/5.0
Behavior4/5

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

The annotations already indicate a safe, read-only, idempotent operation. The description adds meaningful behavioral context by warning against inventing IDs and by instructing the agent to involve the user when selection is required, which goes beyond what the annotations provide.

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?

The description is compact, with each sentence earning its place: first identifies the role in the workflow, then explains what to inspect, then gives last a rule. No redundant or promotional language.

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?

For a candidate-search tool, the description covers the core workflow step, data aspects, user interaction, and prevents hallucination in an appropriate ID. The presence of an output schema and annotations further covers past and return value details. The minimal gap regarding 'limit' is minor.

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?

The schema's description coverage is 50%, with only 'query' explained; however, that explanation is fairly rich and explicit. The tool description supplements it by listing the accepted fields (place name, slug, district, municipality, parish, neighborhood), although it does not clarify the 'limit' parameter.

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?

The description clearly identifies the tool as the first step in location-based operations and states that it finds candidate Casatoo location IDs by place name, slug, district, municipality, parish, or neighborhood. It is distinct from listed siblings, though it does not explicitly name an alternative for comparison.

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?

The description tells an agent when to use it: as Step 1 of every location-based operation. It also gives an explicit workflow rule — inspect selection_state and location_type, and ask the user when selection_required — but it does not spell out when not to use this tool or which sibling should be used instead.

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