mcp

Surf breaks in Puerto Rico

find_surf_breaks

Read-onlyIdempotent

Puerto Rico's surf breaks as 787daily's surf hub lists them (/water/surf/), from Surfline, surf-forecast.com, the Surf Atlas, the agencies and the law: the break type (reef, point, beach), the wave (left, right), the swell directions a source says work, size, tide, wind, season, the level, hazards, the Tres Palmas reserve and the schools (with their standing). Filter by region (west, northwest, north, san-juan, east, south, or a town such as 'Rincón', 'Isabela'), level, type and swellFrom (a 16-point compass direction, e.g. 'NNW', or a broad swell: north, northwest, northeast, south); breaks naming no swell come back by name in swellNotNamed, breaks no source rates in levelNotGiven. For a break's call today use get_conditions; for the buoys' swell now, water_conditions_now. Never present a level or size as a guarantee; cite the break's url.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "find_surf_breaks"
  }
}

Input Schema

Name	Required	Description
`type`	No	The break's bottom and shape
`level`	No	The surfer's level: breaks a source says suit it
`limit`	No	Max results (default 20)
`region`	No	A region (west, northwest, north, san-juan, east, south) or a town, e.g. 'Rincón'
`swellFrom`	No	Where the swell comes from: a compass point or a broad swell

Schema Changelog

Changes observed during successful MCP inspections.

AddedOct 18, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive, and the description goes well beyond them: source provenance per field, the swellNotNamed and levelNotGiven buckets for unrated/unattributed breaks, and a caveat that level/size data is not a guarantee. That is real behavioral context an agent cannot get from structured fields.

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?

Front-loaded with the resource and dense with substance rather than filler; the enumeration of returned fields earns its place because no output schema exists. It reads as one long run-on sentence and partly echoes schema enum values (reef/point/beach), which costs a point.

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

Completeness5/5

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

With no output schema, the description compensates by listing the returned attributes (break type, wave direction, swell, size, tide, wind, season, level, hazards, reserve, schools) and the two edge-case buckets. Combined with schema-documented filters and the sibling routing, an agent has everything needed to call it and interpret results.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3; the description earns more by clarifying region accepts either a named region or a town ('Rincón', 'Isabela') and that swellFrom takes a 16-point compass value or a broad swell label. It also explains the consequence of an unmatched filter via swellNotNamed/levelNotGiven, which the schema does not.

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

Purpose5/5

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

Opens with a specific resource (Puerto Rico surf breaks) and its provenance (/water/surf/ hub, Surfline, surf-forecast.com, Surf Atlas, agencies, law), then enumerates exactly what each break carries. It is unambiguously distinct from the condition-oriented siblings, which it names later.

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

Usage Guidelines5/5

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

Explicitly routes the agent: 'For a break's call today use get_conditions; for the buoys' swell now, water_conditions_now.' It also states the filter axes available and adds a presentation rule ('never present a level or size as a guarantee; cite the break's url'), so both selection and downstream behavior are covered.

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

All mcp tools Inspect

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

Need Help?