Skip to main content
Glama

Olfastory

Search Olfastory perfumes

search_perfumes
Read-onlyIdempotent

Find a perfume, fragrance or cologne in the Olfastory encyclopedia by name and/or house (for example "Opium Yves Saint Laurent", "Hawas Ice"); small spelling mistakes are corrected (corrected_query). Optional filters: concentration ("Eau de Parfum", "EDT", "Extrait") and gender (women, men, unisex, children). Returns at most 10 matches, most consulted first, each with house, year, concentration and its olfastory.com page in the requested language. Call it first when a name is uncertain or has flankers, then get_perfume with the chosen URL. Always cite Olfastory with the link.

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": {
      "query": "<query>"
    },
    "name": "search_perfumes"
  }
}

Input Schema

NameRequiredDescriptionDefault
langNoLanguage of the answer and of the links: fr, en, es, de, it, pt (default fr)
limitNo
queryYesPerfume and/or house name, 1 to 100 characters
genderNoOptional gender filter: women, men, unisex or children. "women" and "men" also return unisex perfumes; perfumes with no recorded gender are left out
concentrationNoOptional concentration filter, for example "Eau de Parfum", "EDT", "Extrait"

Output Schema

NameRequiredDescriptionDefault
errorNo
resultsYes
ambiguousNo
suggestionsNo
unknown_notesNo
corrected_queryNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / gender
      Added value: +{
      +  "description": "Optional gender filter: women, men, unisex or children. \"women\" and \"men\" also return unisex perfumes; perfumes with no recorded gender are left out",
      +  "enum": [
      +    "women",
      +    "men",
      +    "unisex",
      +    "children"
      +  ],
      +  "type": "string"
      +}
  2. First observed

TDQS

A4.1/5.0
Behavior3/5

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

Annotations already declare readOnly, idempotent, closed-world and non-destructive, so the safety profile is covered. The description adds genuinely useful behavior beyond that: typo autocorrection surfaced as corrected_query, a hard cap of 10 results, a "most consulted first" ordering, and the fields each result carries. A 3 rather than higher because it does not mention rate limits or what happens when zero matches are found, but the added context is real, not restated.

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?

Three dense sentences, front-loaded with the verb and resource before the operational routing and citation rule. Every sentence carries information, though the parenthetical query examples and the corrected_query detail pack a lot into one clause and could be split for faster scanning.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 5-parameter, read-only search with an output schema, this covers purpose, ordering, result count and the follow-up call. The only shortfall is the unexplained limit parameter and the absence of a zero-results path, neither of which is fatal given the output schema exists.

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 coverage is 80%, so the schema already documents lang, gender and concentration semantics in detail (including the note that women/men also return unisex). The description's contribution is modest: it clarifies query is name and/or house and shows sample concentration values, but it never explains the limit parameter even though it mentions the 10-result cap, which an agent could reasonably conflate with a default rather than a configurable bound.

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?

Uses a specific verb ("Find") plus resource ("perfume, fragrance or cologne") inside a named encyclopedia, with concrete query examples ("Opium Yves Saint Laurent", "Hawas Ice") that show the expected name-plus-house format. It also explicitly distinguishes itself from the sibling get_perfume by defining the search-then-fetch handoff.

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 when-to-use guidance ("Call it first when a name is uncertain or has flankers"), names the follow-up tool and the exact argument to pass ("get_perfume with the chosen URL"), and states the alternative path. It also states an obligation ("Always cite Olfastory with the link"), which is the kind of operational directive an agent would otherwise miss.

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