get_quakeGet detail for a single New Zealand earthquake by its GeoNet publicID — time, magnitude, depth, locality, felt intensity (MMI), location quality, and coordinates. Keyless.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | GeoNet quake publicID, e.g. "2026p432677" (year + "p" + sequence). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate readOnly, idempotent, and non-destructive behavior. The description adds value by noting 'Keyless' (no authentication required) and specifying the data fields returned. 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?
The description is a single sentence that efficiently communicates purpose, input, and output. It includes the key note 'Keyless' as a fragment. While very concise, it could be slightly restructured for readability, but it 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?
Given no output schema, the description thoroughly enumerates the returned fields (time, magnitude, depth, locality, felt intensity, location quality, coordinates). It also specifies the data source (GeoNet) and that it is keyless. For a simple single-item retrieval tool, this is 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 100%, and the description of the 'id' parameter in the schema is already clear. The tool description reinforces that the ID is a GeoNet publicID but does not add new syntactic details beyond the schema. Baseline 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 retrieves detailed information for a single New Zealand earthquake using its GeoNet publicID. It lists the specific fields returned (time, magnitude, depth, locality, felt intensity, location quality, coordinates) and mentions it is keyless. This distinguishes it from sibling tools like recent_quakes which would list multiple earthquakes.
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 when you have a specific earthquake ID and need its details. However, it does not explicitly state when to use this tool versus alternatives like recent_quakes or volcano_alerts. The guidance is clear but not explicit about exclusions.
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.
Several tools are deliberately near-identical variants (ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded) or have overlapping routing/query purposes (deep_research, validate_claim, discover_tools, suggest_questions). The Polymarket cluster also has five tools that all surface 'edges' or 'arbitrage' with only subtle differences. Only the three GeoNet tools and the memory trio are cleanly distinct.
The dominant style is snake_case, and clusters like ask_pipeworx_* and polymarket_* are internally consistent. However, verb/noun patterns vary widely across the set: some tools begin with verbs (get_quake, scan_dependency, generate_llms_txt), some are noun phrases (entity_profile, volcano_alerts, recent_changes), and some are plain nouns (polymarket_arbitrage). Readable but not a single predictable convention.
34 tools is well above the 'heavy' threshold, and the server is named 'Geonet Nz' while only 3 of its 34 tools relate to GeoNet. The overwhelming majority are Pipeworx/data/prediction-market tools, making the server's scope massively broader than its name implies. The count itself is not unreasonable for the actual feature sprawl, but it is inappropriate for the apparent purpose.
Taking the real scope as 'general authoritative data research + memory + subscriptions + a little GeoNet', the surface is quite complete: query entry points, grounded verification, deep research, entity resolution, comparisons, claim validation, monitoring subscriptions, memory persistence, and feedback are all present. The GeoNet-specific subset is also adequate (get one, list recent, volcano alerts). Minor gaps exist, like no general GeoNet station/well data or subscription editing, but nothing causes dead ends.