Puerto Rico cost-of-living figures from the U.S. Census ACS 5-Year Estimates: median gross rent, median household income, and median home value for the island, the US (comparison), and any of the 78 municipios. Vintage-labeled; suppressed small-town estimates are null.
| Name | Required | Description | Default |
|---|---|---|---|
| town | No | Optional municipio name or slug (e.g. 'Ponce' or 'san-juan'); omit for the island + US summary with all towns |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Input schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It discloses the data source (Census ACS 5-Year), scope (island, US comparison, municipios), vintage labeling, and suppressed small-town estimates being null. These are useful behavioral traits beyond simple retrieval. It stops short of describing the exact return structure, but the listed metrics provide adequate expectation.
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 a single, information-dense sentence that front-loads the core purpose and includes necessary caveats (vintage, nulls) without extraneous words. Every clause adds value.
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?
Given the simple one-parameter schema and no output schema, the description sufficiently covers purpose, source, scope, and edge cases (nulls for suppressed estimates). An agent can correctly select and invoke the tool without further elaboration.
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?
The schema provides 100% coverage of the optional 'town' parameter, including the behavior when omitted (island + US summary with all towns). The tool description adds no additional parameter semantics beyond what the schema already says, so the baseline of 3 is appropriate.
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 clearly states the tool returns Puerto Rico cost-of-living figures from the U.S. Census ACS 5-Year Estimates, listing specific metrics (median gross rent, household income, home value) and geographic scope (island, US comparison, 78 municipios). This is a specific verb+resource that distinguishes it from sibling tools focused on weather, safety, news, and conditions.
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 usage for cost-of-living queries and provides clear context (source, geographic options, null behavior). However, it does not explicitly name alternative tools or state when not to use it. The sibling tools are topically distinct, making the intended use obvious, but the lack of explicit exclusion prevents a 5.
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.
Most tools have clearly distinct purposes: ask synthesizes answers, search_news does semantic retrieval, keyword_search_news does keyword matching, and the get_/list_ tools target specific data types. However, search_pr_news is a redundant alias, and get_by_entity vs get_by_municipality overlap on place queries, creating minor ambiguity.
Tool names use a mix of prefixes (get_, list_, search_) and include a bare verb (ask), which is not fully consistent. The legacy alias search_pr_news further deviates from the pattern, though the rest are readable and predictable.
With 13 tools spanning news, Q&A, weather, cost-of-living, and safety, the count fits the server's broad purpose without being excessive. Each major domain has dedicated tools, and despite one redundant alias, the set remains well-scoped.
The tool set covers article discovery, synthesis, weather, demographics, and safety statistics, providing solid domain coverage. Minor gaps include no full-text article retrieval and no dedicated section browsing, but summaries and links make these workable.