get_packFree discovery. Returns detailed metadata, coverage, freshness, preferred canonical tool guidance, and first-query examples for one pack. Call this before querying a new pack so you can see time shape, coverage limits, and the paste-ready first query.
| Name | Required | Description | Default |
|---|---|---|---|
| pack_id | Yes | Pack identifier from get_catalog. Newly catalog-admitted packs require no MCP schema change. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The readOnlyHint annotation is set, and the description's 'Free discovery' framing aligns with a non-destructive read. The description adds value beyond the annotation by disclosing the nature of what is fetched (time shape, coverage limits, canonical tool guidance, paste-ready examples), which is useful behavioral context for a metadata tool.
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 focused sentences with the core purpose front-loaded before the usage guidance. No wasted words, though the opening 'Free discovery.' is a stylistic flourish that adds little informational 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?
With one required parameter, full schema coverage, a readOnlyHint annotation, and no output schema, the description adequately conveys the return contents (metadata, coverage, freshness, guidance, examples) so an agent knows what to expect. Nothing critical is missing for a single-identifier read 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 coverage is 100% and the schema already documents pack_id as 'Pack identifier from get_catalog.' The description adds no parameter-specific detail, but at high coverage the baseline of 3 applies; the schema carries the semantic load and does so adequately.
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 states a clear verb+resource: it returns detailed metadata, coverage, freshness, canonical tool guidance, and first-query examples for one pack. The phrase 'one pack' distinguishes it from the sibling get_catalog, which enumerates packs. It opens with a vague marketing phrase ('Free discovery'), but the substantive purpose is unambiguous.
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?
Explicitly instructs when to call: 'Call this before querying a new pack so you can see time shape, coverage limits, and the paste-ready first query.' This gives a clear temporal trigger. However, it does not name the specific alternative (get_catalog) for discovering pack IDs or state when not to use it, leaving some routing to 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 has a clearly distinct purpose: point resolution, reference conversion, hierarchy traversal, geometry retrieval, export creation, job estimation, catalog discovery, and relationship comparison are all separated. The descriptions explicitly state what each tool does and what it does not do, preventing misselection. Even closely related tools like get_geometry, get_geometry_export, and estimate_geometry_package are differentiated by their roles (single-shape retrieval vs. export artifact vs. dry-run estimate).
All 20 tool names follow a consistent verb_noun snake_case pattern (e.g., get_geometry, create_conversion_job, resolve_point, list_reference_systems). The verbs are action-oriented (get, create, estimate, resolve, compare, list, read) and each noun clearly indicates the subject. While a few like 'loc_id_info' and 'how_geometry_works' deviate slightly from the strict verb_noun structure, they still fit the overall style and are easy to predict.
The 20 tools are slightly above the typical 3-15 range but still well-scoped for a comprehensive geocoding and geography service. The extra tools reflect the breadth of operations offered (discovery, conversion, estimation, export, resolution, relationship analysis), each earning its place. The count feels reasonable given the domain, though it approaches the upper boundary of what an agent might easily navigate.
The tool surface covers the full lifecycle of geocoding workflows: discovery (get_catalog, get_pack, read_geometry_catalog), point resolution (resolve_point), reference resolution (resolve_reference), identifier identification (identify_reference_system), hierarchy traversal (resolve_loc_id_scope, loc_id_info), geometry retrieval (get_geometry), relationship analysis (compare_geographies), conversion (convert_reference, create_conversion_job), export (create_geometry_export), and estimation (estimate_geometry_package, estimate_conversion_job). The inclusion of help tools (get_tool_help, how_geometry_works) and job status retrieval ensures no dead ends. The absence of destructive or update operations is consistent with a read-only geospatial data service, so the surface is appropriate.