Skip to main content
Glama

add_river

Draws a meandering river through specified points, from source to sea or lake, on land only, with configurable width and seed.

Instructions

Add a meandering river through points (first point is the source; end it in the sea or a lake); drawn on land only. width is in px at full width; the river narrows towards its source over its first few widths.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "points": "<points>"
    },
    "name": "add_river"
  }
}

Input Schema

NameRequiredDescriptionDefault
seedNoRandom seed (0 to 2^32-1); the same seed gives the same result.
widthNo
pointsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.6/5.0
Behavior3/5

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

With no annotations at all, the description carries the full burden. It usefully discloses rendering behavior — meandering path, land-only placement, tapering toward the source over the first few widths — but says nothing about what happens if points fall in water, whether the river can be removed or undone afterward, or what the call returns.

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

Conciseness5/5

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

A single dense sentence with parenthetical clauses; the verb and resource lead, and each clause (source point, endpoint, land-only, width units, tapering) contributes distinct information without redundancy.

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

Completeness3/5

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

For a three-parameter mutation with no annotations and no output schema, the definition covers the geometry contract well but leaves gaps: behavior on invalid or off-land input, undo/removal interaction, and any confirmation of the created object are unaddressed.

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 only 33%, so the description must compensate, and it largely does: it explains that the points array is ordered with the first element as source, and that width is a full-width value in pixels that visually tapers upstream. Only the seed is explained elsewhere (in the schema), leaving width's unit established but not its valid range.

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?

The description uses a specific verb and resource ('Add a meandering river') and immediately clarifies the geometry contract (first point is source, terminate in sea or lake, drawn on land only). It doesn't name a sibling such as add_lake or add_path to sharpen differentiation, but the operation itself is unambiguous.

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?

Usage is implied rather than stated: the parenthetical establishes a required topology (source first, mouth in sea/lake) and a land-only restriction, which functions as a prerequisite. There is no explicit when-to-use/when-not guidance and no routing to alternatives like add_lake for water bodies or add_path for non-water lines.

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