Skip to main content
Glama

What Stands Out About a Boat

get_boat_standouts
Read-only

What stands out about ONE boat for one week, measured against similar boats: its pros and its cons, each with how it compares ("47.9 ft (better than 99%)", "€2000 security deposit (typical €1700)", "Rare kit: [0.8%] Cool Box" — n% of those boats have it). Use when the guest asks what is special about a boat, what the catch is, why it is cheap or dear, or how it compares with others. It measures build year, length, cabins, bathrooms, guests, the security deposit and kit — and, with date_from, check-in and check-out times, the changeover day and the open weeks left; any of those it does not list is ordinary among the boats in compared_with, so do not sell it as an edge or a catch. Other fees are not compared. Kit is measured two ways and both hold: get_boat_details gives each item its [n%] across the whole fleet, this tool what is rare among boats like it. rare_kit lists that rare kit as data, most useful first, each with useful_score (1-5: how much it changes a charter week for the people aboard). note says whether an absence means "ordinary" or that nothing could be compared.

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": {
      "id": "<id>"
    },
    "name": "get_boat_standouts"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYesBoat id from search_boats or get_boat_details — copy it verbatim.
currencyNoOptional: the currency every amount in the answer is written in, and any price you send is read in. When the conversation has its own currency, that one is used whatever is sent; otherwise the one sent, EUR when omitted.
fallbackNoOptional, default true: with nothing past the cut-off on a side, name the one thing that beats (or trails) most of them. false returns only what clears the cut-off.
date_fromNoOptional check-in date YYYY-MM-DD of the week the guest is looking at: the boats are then compared on that week's prices, and its schedule and open weeks are judged. Pass it whenever the guest has dates.
compare_byNoWhich boats count as similar. price (default): the same type priced within ±5% — what else the same money buys. guests: the same type taking the same number of guests — use when the question is value for a party size ("is it cheap for 10 people?"). length: the same type within ±2.5% of its length — use when comparing boats of one size. On guests and length the all-in day rate (the figure the search card prints) is compared too.
cutoff_pctNoOptional, default 10, at most 50: a pro beats all but this share of the similar boats, a con trails all but it, rare kit is on fewer than it. Raise it for more, weaker lines.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / currency / description
      Previous value: -"Optional: the currency every amount in the answer is written in, and any price you send is read in. EUR when omitted."New value: +"Optional: the currency every amount in the answer is written in, and any price you send is read in. When the conversation has its own currency, that one is used whatever is sent; otherwise the one sent, EUR when omitted."
  2. Changed1 schema field changed
    • addedInput schema / properties / currency
      Added value: +{
      +  "description": "Optional: the currency every amount in the answer is written in, and any price you send is read in. EUR when omitted.",
      +  "enum": [
      +    "EUR",
      +    "USD"
      +  ],
      +  "type": "string"
      +}
  3. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already cover the read-only, non-destructive, closed-world profile, yet the description adds substantial behavior: unlisted attributes mean 'ordinary' among the compared set and must not be sold as an edge or a catch, other fees are excluded, the `note` field disambiguates an absence versus nothing comparable, and `fallback`/`cutoff_pct` shape how weak lines appear. This is exactly the interpretive context annotations cannot 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 the concrete comparison-string examples are front-loaded, and each paragraph carries a distinct load (what it measures, what absence means, how kit differs from get_boat_details, what the output fields are). It is dense and long for a single tool, and the parenthetical example list is heavier than strictly needed, but no sentence is filler.

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 carries the full burden of explaining returns and does so: the pros/cons comparison format, the rare_kit data list with useful_score, and the `note` semantics. It also states the absence-means-ordinary rule that an agent would otherwise misread. Nothing needed to call or interpret it correctly is missing.

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 baseline is 3, but the description adds meaning on top: it explains that the compared set is defined by `compared_with` and that date_from switches on schedule, changeover day, and open-weeks judgments. It also clarifies the rare_kit output ordering via useful_score, which links parameter choice to interpretation. The gain over the schema text is real but modest, since compare_by and cutoff_pct are already well documented.

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 description opens with a specific verb and scope: what stands out about ONE boat for one week, measured against similar boats, returning pros and cons with comparison strings. It concretely enumerates the measured dimensions (build year, length, cabins, bathrooms, guests, security deposit, kit) and explicitly names the sibling split — get_boat_details for fleet-wide kit percentages versus this tool for rarity among comparable boats. An agent can distinguish it from get_boat_details without opening either schema.

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

Usage Guidelines4/5

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

It gives explicit trigger conditions: guest asks what is special, what the catch is, why it is cheap or dear, or how it compares with others. It also warns against over-selling ordinary attributes when date_from is absent and notes that other fees are not compared, which is a useful scope exclusion. The one gap is that compare_boat — a sibling with overlapping comparison semantics — is never mentioned, so the pairwise-versus-benchmark choice is left to inference.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.