Skip to main content
Glama
Garden Design MCP Server

Garden Design MCP Server

search_plants

Filter the plant catalog by botanical attributes like soil, sunlight, height, bloom period, and hardiness, then return lean plant records. Use get_plant_attributes to find valid filter values.

Instructions

Filter the plant catalog by botanical attributes. Returns lean records ({productId, code, botanicalName, commonName}). Call get_plant_attributes first to discover valid filter values for the current locale. Multi-value filters use OR semantics (any value matches); different filters are AND-combined. Range filters use overlap semantics (a plant's range must intersect the requested range). Capped at limit (default 25, max 100); response includes total + truncated flag. Use get_plant_info for full per-plant details after picking a candidate. Falls back to a loud error if the index is unavailable on the CDN — agents should retry name-based queries via search_products in that case.

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": "search_plants"
  }
}

Input Schema

NameRequiredDescriptionDefault
soilNoOR-match against the plant's soil array. Use values from get_plant_attributes.soil.
limitNoMax matches returned (default 25, clamped to [1, 100]). The total count of all matches is always returned, so you can detect truncation.
queryNoOptional substring match (case-insensitive) on botanicalName OR commonName. No diacritic stripping — pass terms as they appear in the locale (e.g. 'Jeżówka', not 'jezowka'). Exact matches are ranked first.
heightNoOverlap match: the plant's height range must intersect [min, max] (inclusive). Values are in METERS regardless of set_units (this is plant size, not editor coordinates).
spreadNoOverlap match in METERS, same semantics as height.
sunlightNoOR-match against the plant's sunlight array. Use values from get_plant_attributes.sunlight.
hardinessNoOverlap match against the plant's USDA hardiness zone range.
bloomPeriodNoOR-match against the plant's bloomPeriod array. Roman months I–XII; use get_plant_attributes.bloomPeriod.
flowerColorNoOR-match against the plant's flowerColor array. Use values from get_plant_attributes.flowerColor.
foliageTypeNoExact match against the plant's foliageType. Use a value from get_plant_attributes.foliageType.
divisionNeededNoExact match.
pruningTolerantNoExact match.
maintenanceLevelNoOR-match against the plant's maintenanceLevel. Use values from get_plant_attributes.maintenanceLevel.
hasOrnamentalBarkNoExact match.
hasOrnamentalFruitNoExact match.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv2.9.3

TDQS

A4.8/5.0
Behavior5/5

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

With no annotations supplied, the description carries the full burden and does so: it discloses the lean return shape ({productId, code, botanicalName, commonName}), the OR-within/AND-across filter combination rule, range overlap semantics, the default 25 / max 100 cap with total + truncated flag, and a loud-error failure mode with a prescribed recovery. This is exactly the behavioral context annotations would otherwise have to supply.

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?

Purpose and return shape are front-loaded, followed by preconditions, then semantics, then the failure path — a sensible ordering with no filler sentences. It is dense and long for a single description, and the CDN-error sentence could be trimmed, but each sentence conveys operational information an agent would otherwise have to guess.

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?

For a 15-parameter, fully-optional filter tool with nested range objects and no output schema, the description supplies everything missing: what comes back, how results are bounded and how truncation is detected, how filters compose, and what to do when the backend fails. Nothing an agent needs in order to call this correctly and interpret the response is absent.

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 per-parameter descriptions already establish the baseline. The description adds value beyond the schema by stating the cross-parameter logic that no single field can express: multi-value filters OR together while different filters AND-combine, and range filters use intersection rather than containment. It does not restate the per-field value sourcing, which is fine given the schema already covers it.

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?

The opening sentence names a specific verb and resource ('Filter the plant catalog by botanical attributes') and explicitly positions itself against three siblings: get_plant_attributes for discovering filter values, get_plant_info for full details, and search_products as the fallback path. An agent can distinguish this from every other search-ish sibling without opening a schema.

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?

The description gives ordered, conditional guidance rather than mere context: call get_plant_attributes first for valid locale values, then this tool, then get_plant_info on the picked candidate. It also names a concrete when-not path (if the index is unavailable, retry name-based queries via search_products).

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