Citable facts about boats and watersports from Obato's knowledge graph, ranked by authority score. Each fact includes a source citation suitable for grounded LLM answers.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Number of facts to return. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare read-only, open-world=false, non-destructive. The description adds that facts are ranked by authority score and each includes a citation, which is useful for LLM grounding. It does not contradict annotations.
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?
Two concise sentences that front-load the core purpose and mention ranking and citations without any fluff.
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?
For a tool with one param, fully described in schema, the description gives adequate context about the nature of the data (ranked, cited) even without an output schema. Some might want more on how authority is defined, but it's sufficient for basic selection.
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?
The schema fully describes the 'limit' parameter (default, min, max). The description adds no additional parameter context, so baseline 3 is appropriate given 100% schema coverage.
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 returns citable facts about boats and watersports from Obato's knowledge graph, ranked by authority score. This distinguishes it from sibling tools like get_boat_details or get_market_stats, which focus on specific entities or market data.
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?
It implies usage for grounded answers with citations, but does not explicitly state when to use this tool versus alternatives like ask_bo or search_boats. No exclusions or comparisons are provided.
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.
Most tools target distinct resources, but get_boat_pricing_stats and get_market_stats overlap heavily: both return count, average, median, min/max price scoped by category and region. ask_bo and get_facts also both return cited factual content, leaving some ambiguity even if the descriptions help.
The set predominantly follows a verb_noun pattern: search_boats, search_rentals, get_brand_info, compare_brands, and get_boat_details all fit cleanly. market_snapshot breaks the pattern as a bare noun phrase, and ask_bo uses a proper noun, but these are minor deviations within an otherwise predictable convention.
11 tools is well-scoped for a multifaceted read-only marketplace domain covering listings, rentals, brands, marinas, knowledge-graph facts, and market statistics. Each tool earns its place, even though a couple of them partially overlap.
Core workflows are covered: boat search and details, rental search, brand lookup and comparison, marina discovery, knowledge-graph facts, and multiple market statistics views. Minor gaps exist, such as no dedicated marina detail endpoint and rental details only appearing via search results, but agents can work around these.
