finn-seller-mcp

Overview Schema Source Related Servers Discussions Admin

create_draft

Creates a local draft ad with processed photos, price, and category, ready for final review before publishing to finn.no.

Instructions

Create a LOCAL draft ad (nothing is sent to finn.no yet).

    Photos are auto-rotated, stripped of EXIF/GPS and resized; the first
    photo is the cover. category = numeric LEAF id (e.g. "43" Bærbar PC;
    use suggest_category after push_draft if unsure). condition: 1=Helt ny
    2=Som ny 3=Pent brukt 4=Godt brukt 5=Må fikses. trade_type: 1=Til salgs.
    Price is in whole NOK.

    PRICE POLICY: if the user named a price, use exactly that. Otherwise call
    suggest_price first and use its `suggested_price` (market median), and
    tell the user which comparables it is based on.

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": {
      "title": "<title>",
      "description": "<description>",
      "photo_paths": "<photo_paths>"
    },
    "name": "create_draft"
  }
}

Input Schema

Name	Required	Default
`price`	No
`title`	Yes
`category`	No
`condition`	No
`attributes`	No
`trade_type`	No	1
`description`	Yes
`photo_paths`	Yes
`postal_code`	No
`photo_captions`	No

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.2.0Oct 25, 2026

TDQS

A4.4/5.0

Behavior4/5

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

No annotations exist, so the description carries the full burden, and it does well: it discloses that the draft is local-only, that photos are auto-rotated, EXIF/GPS-stripped and resized, and that the first photo becomes the cover. It does not disclose authentication/prerequisite state or what happens to existing drafts on repeat calls, leaving some behavioral gaps for an unannotated mutation tool.

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 the single most important fact (local, nothing published), then compact enum glossaries and a clearly labelled PRICE POLICY block. Slightly longer than needed, and the parenthetical 'use suggest_category after push_draft if unsure' is easy to misread as an instruction for this call rather than a later one.

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 10 parameters, no annotations and an output schema present, the description covers the world-facing essentials: environment (local), side effects on photos, enum code meanings, currency units, and the price-decision policy. Remaining undocumented fields (attributes, postal_code, captions) are optional conveniences rather than things needed to call the tool correctly.

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 description coverage is 0%, so the description must compensate, and it does for the hard parameters: category as a numeric LEAF id with an example, all five condition codes spelled out, trade_type 1=Til salgs, and price as whole NOK. Five of ten parameters (title, description, attributes, postal_code, photo_captions) still get no semantic explanation anywhere.

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?

Specific verb+resource: 'Create a LOCAL draft ad', immediately qualified with '(nothing is sent to finn.no yet)', which cleanly separates it from push_draft and publish_draft. An agent can tell which of the draft-related siblings to call 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 Guidelines4/5

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

Explicit pre-call routing is given for price (use the user's named price, otherwise call suggest_price first and cite comparables) and for category (fall back to suggest_category via push_draft). No explicit exclusion such as 'use update_draft to modify an existing draft', so the when-not case is left implicit.

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