Skip to main content
Glama

Sedna search guidance

readme
Read-onlyIdempotent

Sedna guidance for public yacht-search conversations.

  1. Yacht, fleet, availability and price facts come from Sedna tool results; do not invent them.

  2. Stay neutral between fleets. Present factual differences and let the customer decide.

  3. Call Base_list before search_boats so the search uses an official base.

  4. Copy id_boat and id_tbf1 exactly as returned by search_boats.

  5. When the customer does not state a year, clarify the date or use the current year rather than silently choosing another year.

  6. When the customer asks to see yacht photos or other yacht media, call boat_details with the exact id_boat from search_boats. Display the public URLs returned in media.header, media.photos, media.plans or media.images. search_boats intentionally returns no gallery. Use booking_detail only for date-specific availability, prices, extras and booking choices.

  7. A search result is available only for the requested dates reported by Sedna. Never generalize that availability to different dates.

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": "readme"
  }
}

Input Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Annotations only declare this is a safe read; the description adds real behavioral context beyond that: ID fields must be copied verbatim, search_boats returns no media, media is exposed through media.header/photos/plans/images on boat_details, and availability must never be generalized to other dates. It also flags the no-invention and fleet-neutrality constraints, which annotations cannot express.

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 a one-line scope statement, then a numbered rule list where each item is actionable and self-contained. Rule 6 is noticeably longer than the others and mixes media guidance with booking_detail guidance, but no rule 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?

For a zero-parameter, no-output-schema guidance tool, the description supplies everything an agent needs: data provenance, ordering prerequisites, cross-tool field contracts, and date-scoping limits. Nothing essential is left to inference given the tool's simplicity.

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?

The tool takes zero parameters, so the baseline is 4 and there is no schema surface the description needs to compensate for. The description uses the space instead to document the identifier fields (id_boat, id_tbf1) that flow between sibling tools.

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 opens with 'Sedna guidance for public yacht-search conversations,' which tells the agent this tool returns operating rules rather than data. It also names the concrete siblings it routes to (Base_list, search_boats, boat_details, booking_detail), so it is distinguishable from them. It stops short of a single crisp verb+resource statement of what the call returns.

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?

Rules 3, 6 and the final rule give explicit ordering ('Call Base_list before search_boats'), explicit tool selection ('use booking_detail only for date-specific availability, prices, extras') and explicit exclusion ('search_boats intentionally returns no gallery'). Alternatives and their selecting conditions are stated rather than inferred.

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.

Resources