list_facilitiesList Georgia prison facilities with location, operator, security level, capacity, population, warden and latest food-safety score.
Optional filters are applied to the public list after it is fetched:
facility_type (e.g. 'State Prison', 'Transitional Center', 'County
Prison'), county, name_contains, and active_only.| Name | Required | Description | Default |
|---|---|---|---|
| county | No | ||
| active_only | No | ||
| facility_type | No | ||
| name_contains | No |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so safety is covered. The description adds meaningful behavioral context beyond annotations: filters are 'applied to the public list after it is fetched,' which discloses client-side filtering behavior rather than server-side querying. It also states the full set of returned fields, giving the agent a clear picture of output shape.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences: the first delivers the core purpose and output fields; the second concisely lists filters and an example. There is no fluff, and the most actionable information is front-loaded. Every sentence earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema, the description compensates by enumerating the returned fields, which is sufficient for an agent to know what to expect. It also explains filter behavior and defaults (though defaults come from the schema). Missing pagination or ordering details are minor for a simple listing tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description carries the full burden for explaining parameters. It names all four parameters (facility_type, county, name_contains, active_only) and provides examples for facility_type ('State Prison', 'Transitional Center', 'County Prison'). It also clarifies the semantics of filtering as applied post-fetch. This substantially compensates for the empty schema, though it leaves some format details (e.g., exact county matching) implicit.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description opens with a specific verb ('List') and a precise resource ('Georgia prison facilities'), and enumerates the exact fields returned (location, operator, security level, capacity, population, warden, food-safety score). It is clearly distinguishable from sibling tools like get_facility (single facility) and list_intelligence (intelligence entries).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies its use case by describing the tool's listing behavior and available filters, but it does not explicitly state when to choose this tool over alternatives such as get_facility or when not to use it. The filter explanation gives context, but no direct exclusions or alternative routing.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool names a distinct resource or action: contraband incidents vs summaries, a single facility vs facility list vs staff roster, and site-wide search vs quote search. The few close pairs are complementary rather than duplicative, and descriptions explicitly indicate when to use each.
All tool names follow a consistent snake_case verb_noun pattern (get_*, list_*, search_*). The one outlier, get_gps_guide, still fits the get_<resource> convention, so there is no real style clash.
At 18 tools the server is heavier than a minimal CRUD surface, but it covers a broad public-data domain with a distinct endpoint per dataset or site function. The count feels slightly over the typical sweet spot rather than bloated or redundant.
The major GPS data domains are represented: facilities, population, mortality, contraband, parole, length of stay, settlements, and legal text. A few potentially relevant datasets (e.g., a structured budget tool) are not exposed directly, but search_site plus get_page cover most of those gaps.