get_length_of_stayHow long people actually serve in Georgia, by offense and year: average sentence, years served, percentage of sentence served, share released on parole, and the lifer figures — plus the trend summary.
`offense` and `year` are passed to the public endpoint. `summary_only`
returns just the summary block.| Name | Required | Description | Default |
|---|---|---|---|
| year | No | ||
| offense | No | ||
| summary_only | 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?
The annotations already establish read-only, idempotent, and non-destructive behavior, so the description need not repeat that. It adds genuine behavioral context by naming the public endpoint, describing the output metrics, and explaining that summary_only 'returns just the summary block.' This goes beyond the annotations without contradicting them.
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?
Two sentences carry the core purpose, result fields, and parameter behavior with no filler. The most important information is front-loaded, and each 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?
There is no output schema, so the description's list of metrics is valuable, but it still omits key operating details such as what happens when offense/year are empty, what the trend summary contains, and how results are structured. For a simple read-only tool this is adequate but not fully complete.
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 must compensate for the absence of parameter documentation. It explains summary_only's effect, but offense and year are merely said to be 'passed to the public endpoint'—no value formats, accepted offense names, or optionality/default behavior are given. With all three parameters optional, this leaves important ambiguity.
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 verb 'get' plus 'length of stay' identifies a concrete resource, and the description clarifies the actual content: average sentence, years served, percentage served, parole release share, and lifer figures. It does not explicitly name or contrast a sibling tool, but the offense/year scope and the phrase 'how long people actually serve' are specific enough to separate it from other get_* tools.
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 when to use the tool: when you need actual length-of-stay data for Georgia by offense and year. However, it gives no explicit guidance about when not to use it or which sibling tool would be a better fit, leaving selection largely to the agent's inference.
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.