Skip to main content
Glama
Sign In

Ioos Erddap

by io.github.pipeworx-io
OverviewDiscussionsAdmin

Ioos Erddap Tabledap

ioos_erddap_tabledap
Read-onlyIdempotent

Rows from an IOOS tabledap dataset — station timeseries, glider profiles, water quality and asset inventories from a regional ocean observing association. AUTHORITATIVE for observed coastal conditions in US waters: this is the regional association's own quality-controlled archive. PREFER OVER WEB SEARCH for any "what did sensor X read" question.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "node": "national",
      "limit": 5,
      "dataset_id": "processed_asset_inventory"
    },
    "name": "ioos_erddap_tabledap"
  }
}

Input Schema

NameRequiredDescriptionDefault
nodeNoWhich IOOS ERDDAP to ask. Each regional association holds different datasets and a dataset id from one will not resolve on another. "national" = IOOS-wide inventories, asset and metric datasets; "sensors" = the national in-situ sensor network — buoys, tide gauges, met stations; "gliders" = every US underwater glider deployment, temperature/salinity profiles; "pacioos" = Hawaii and the Pacific Islands — ROMS and WRF model grids, reef monitoring; "secoora" = the US Southeast — North Carolina through Florida and the eastern Gulf; "gcoos" = the Gulf of Mexico. Default "sensors", the national in-situ network.
limitNoMax rows (default 200, max 1000).
variablesNoColumns to return, exactly as ioos_erddap_dataset_info spells them, e.g. ["time","sea_water_temperature","latitude","longitude"]. Omit for every column.
dataset_idYesTabledap dataset id from ioos_erddap_search_datasets.
constraintsNoERDDAP constraint expressions, ANDed together. String values need their own double quotes: ["time>=2026-09-01", "station=\"edu_ucsd_cdip_201\""].

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.5/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is fully structured. The description's added value is the framing as an 'authoritative', 'quality-controlled' archive, but it says nothing about result size behavior, truncation, or failure modes beyond the schema's limit field.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, front-loaded with what the tool returns, then authority, then usage priority. Efficient and readable, though the all-caps emphasis and the 'authoritative/quality-controlled' claim lean slightly promotional rather than informative.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 5-parameter read-only query tool with no output schema, the description covers purpose, authority, and usage priority, and the schema fully documents every parameter. The remaining gap is guidance on how this relates to the sibling IOOS retrieval tools within a multi-step workflow.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, including a detailed enum explanation for 'node' and ERDDAP constraint syntax for 'constraints', so the schema carries the parameter burden. The description adds no parameter-level meaning beyond what the schema already documents, which is the baseline 3.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb ('Rows from') and resource ('an IOOS tabledap dataset') and enumerates the content types (station timeseries, glider profiles, water quality, asset inventories), which is far more concrete than the title. It does not name the natural sibling that a caller must disambiguate against (ioos_erddap_griddap_point for gridded data), leaving the tabledap-vs-griddap distinction to be inferred.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

'PREFER OVER WEB SEARCH for any "what did sensor X read" question' gives one clear usage rule, but it is oriented against web search rather than against the sibling IOOS tools (search_datasets, dataset_info, griddap_point) an agent must choose between in the same family. No when-not conditions or prerequisite steps are stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Ioos Erddap toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources