10ML Perfume Finder

Compare perfumes

compare_perfumes

Read-onlyIdempotent

Compare 2 to 4 perfumes side by side: notes they share, notes only one has, accords, family, audience, launch year, longevity and projection, plus plain-language differences ('A is fresher, B is sweeter and lasts longer') and how close they are overall. Use when someone is choosing between named perfumes or asks how two differ ('Sauvage vs Bleu', 'Delina or Layton'). Not for finding perfumes like one (use find_similar_perfumes) and not for one perfume's details (use get_perfume).

Input Schema

TableJSON Schema

Name	Required	Description	Default
`locale`	No	Language of the 10ml.com links and labels. Perfume, house and note names stay as they are.	en
`perfumes`	Yes	2 to 4 perfumes, each a name with optional house or an id. Example: ["Dior Sauvage","Tom Ford Ombre Leather"]
`response_format`	No	concise (default) or detailed (adds note pyramid, seasons, occasions, longevity, projection).	concise

Output Schema

TableJSON Schema

Name	Required	Description	Default
`source`	Yes
`message`	No
`perfumes`	Yes
`closeness`	Yes
`unresolved`	No
`differences`	Yes
`shared_notes`	Yes
`unique_notes`	Yes
`shared_accords`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed15 schema fields changedOct 20, 2026
- removedOutput schema / properties / closeness / description
```
Removed value: -"How alike the perfumes are overall (average over all pairs)"
```
- removedOutput schema / properties / differences / description
```
Removed value: -"Plain-language differences, most important first"
```
- removedOutput schema / properties / perfumes / items / properties / accords / description
```
Removed value: -"Main accords, strongest first"
```
- removedOutput schema / properties / perfumes / items / properties / character / description
```
Removed value: -"One-sentence description by 10ML's fragrance editors"
```
- removedOutput schema / properties / perfumes / items / properties / family / description
```
Removed value: -"Fragrance family, e.g. \"amber floral\""
```
- removedOutput schema / properties / perfumes / items / properties / id / description
```
Removed value: -"Stable Fragrance Index id, usable with get_perfume and find_similar_perfumes"
```
- removedOutput schema / properties / perfumes / items / properties / key_notes / description
```
Removed value: -"The defining notes (empty when no pyramid is published)"
```
- removedOutput schema / properties / perfumes / items / properties / links / description
```
Removed value: -"1-3 relevant 10ml.com links"
```
- removedOutput schema / properties / perfumes / items / properties / links / items / properties / url / description
```
Removed value: -"A 10ml.com link in the requested locale"
```
- removedOutput schema / properties / perfumes / items / properties / longevity / description
```
Removed value: -"1 (short) to 5 (very long)"
```
- removedOutput schema / properties / perfumes / items / properties / other_versions / description
```
Removed value: -"Ids of other concentrations or flankers of the same perfume in the index"
```
- removedOutput schema / properties / perfumes / items / properties / projection / description
```
Removed value: -"1 (skin scent) to 5 (fills a room)"
```
- removedOutput schema / properties / perfumes / items / properties / year / description
```
Removed value: -"Launch year when known"
```
- removedOutput schema / properties / shared_notes / description
```
Removed value: -"Notes present in every compared perfume"
```
- removedOutput schema / properties / unique_notes / description
```
Removed value: -"Per perfume id: notes the others do not have"
```

Changed2 schema fields changedOct 20, 2026

addedOutput schema / properties / perfumes / items / properties / profile

Added value: +{
+  "enum": [
+    "full",
+    "core"
+  ],
+  "type": "string"
+}

changedOutput schema / properties / perfumes / items / required

Previous value: -[
-  "id",
-  "name",
-  "house",
-  "gender",
-  "family",
-  "accords",
-  "key_notes",
-  "character",
-  "links"
-]New value: +[
+  "id",
+  "name",
+  "house",
+  "gender",
+  "family",
+  "accords",
+  "key_notes",
+  "character",
+  "links",
+  "profile"
+]

Changed9 schema fields changedOct 19, 2026

removedInput schema / $schema

Removed value: -"http://json-schema.org/draft-07/schema#"

changedInput schema / properties / locale / description

Previous value: -"Language of the 10ml.com links and fixed labels: en, de, fr, es, it, ro, el, hu, cs or pl. Perfume, house and note names are never translated."New value: +"Language of the 10ml.com links and labels. Perfume, house and note names stay as they are."

changedInput schema / properties / response_format / description

Previous value: -"concise (default): the essentials, about a third of the size. detailed: adds the full note pyramid, seasons, occasions, longevity and projection."New value: +"concise (default) or detailed (adds note pyramid, seasons, occasions, longevity, projection)."

removedOutput schema / $schema

Removed value: -"http://json-schema.org/draft-07/schema#"

removedOutput schema / additionalProperties
```
Removed value: -false
```
removedOutput schema / properties / perfumes / items / additionalProperties
```
Removed value: -false
```
removedOutput schema / properties / perfumes / items / properties / links / items / additionalProperties
```
Removed value: -false
```
removedOutput schema / properties / perfumes / items / properties / pyramid / additionalProperties
```
Removed value: -false
```
removedOutput schema / properties / unresolved / items / additionalProperties
```
Removed value: -false
```

AddedOct 19, 2026

TDQS

A4.5/5.0

Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so safety is covered; the description adds the comparison scope (side-by-side dimensions) and the style of output ('plain-language differences', overall closeness), which is useful behavioral context. It stops short of noting output size or the effect of response_format beyond what the schema states.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core action in the first clause, then examples, then exclusions. Each sentence carries distinct information with no filler or repeated schema content.

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?

An output schema exists, so return values need no explanation, and the description still supplies everything else an agent needs: comparison scope, trigger conditions, and disambiguation from the nearest siblings. Nothing required to select or call the tool correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%: the perfumes array (2-4 items, name with optional house or id), locale enum, and response_format are all fully documented in the schema. The description's only parameter-relevant statement is the 2-to-4 range, which duplicates maxItems/minItems, so baseline 3 applies.

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?

States a specific verb (compare) and resource (2-4 perfumes) and enumerates exactly what dimensions are compared: shared/unique notes, accords, family, audience, year, longevity, projection, plus natural-language verdicts. It names two sibling tools it is not (find_similar_perfumes, get_perfume), so an agent can route without opening other schemas.

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?

Gives explicit trigger conditions with example phrasings ('Sauvage vs Bleu', 'Delina or Layton') and explicit exclusions with the correct alternatives for each. Nothing is left to inference for an agent deciding between compare_perfumes, find_similar_perfumes, and get_perfume.

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

All 10ML Perfume Finder tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.