Your own closet in your AI: outfits from clothes you own, rendered on a model inline.
Scored across 3 tools
about_outfitmaker is clearly informational, but suggest_outfit and what_to_wear_today overlap substantially by both producing outfit recommendations. The distinction is mostly temporal/weather-specific versus formula-based, which is helpful but still easy to confuse.
All names use snake_case, but the patterns vary: one is an informational about_* name, one is verb_noun, and one is a question-like phrase. The set is readable but does not follow a single predictable naming convention.
Three tools is slightly thin but reasonable for a focused outfit-suggestion assistant. Each tool has a plausible role, though the surface could benefit from one or two more tools for wardrobe or preference handling.
The core suggestion workflow is covered, including general occasion/weather formulas and daily forecast-based recommendations. However, there are notable gaps around managing a closet, saving preferences, or providing feedback, which the server's own about text implies are part of the value proposition.
What OutfitMaker is and what connecting your own closet unlocks (AI outfits from your real clothes, daily weather-aware looks, on-model previews).
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds that the tool surfaces product capabilities rather than performing an action, which is mildly useful, but says nothing about output form, length, or any side effects beyond the annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single sentence with a front-loaded purpose clause and a compact parenthetical of examples. It is appropriately sized, though the parenthetical list is slightly dense.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a parameterless, read-only info tool with no output schema, the description is complete enough: it tells the agent what the call returns (an explanation of the product and its unlocked features). Only the exact return format is unspecified, which is a minor gap.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool takes zero parameters, so the schema-description burden is nil and the baseline of 4 applies. Nothing in the description conflicts with the empty schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description makes clear this is an informational tool that explains what OutfitMaker is and what connecting a closet unlocks, listing concrete capability examples (AI outfits, weather-aware looks, on-model previews). It is distinguishable from the action-oriented siblings suggest_outfit and what_to_wear_today, though it never explicitly names them.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no statement of when to call this tool versus suggest_outfit or what_to_wear_today. The onboarding/FAQ framing is only implied by the content of the parenthetical list, and no trigger conditions or exclusions are given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get curated outfit formulas for an occasion and weather. Occasions: casual, school, work, date, party, friends, formal.
| Name | Required | Description | Default |
|---|---|---|---|
| occasion | Yes | The occasion (required) | |
| wind_kmh | No | Wind speed in km/h — 25+ changes footwear advice (optional) | |
| condition | No | Weather condition — rain/snow change the outfit, clouds do not (optional) | |
| temperature_c | No | Outside temperature in °C (optional) | |
| temperature_max_c | No | Afternoon high in °C (optional) | |
| temperature_min_c | No | Morning low in °C — with max, unlocks layering advice for big day swings (optional) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds that output is 'curated outfit formulas' (i.e., preset recommendations, not personalized styling), but discloses nothing about permissions, determinism, or return shape beyond that.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, purpose front-loaded, occasion list trailing. Zero filler; every clause carries information the agent needs to form the call.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Read-only tool with no output schema, so the description needn't explain returns — but 'curated outfit formulas' is vague about what actually comes back, and with no guidance against the near-identical sibling the definition is only minimally sufficient for correct selection.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the baseline is 3, but the description enumerates the valid occasion values (casual, school, work, date, party, friends, formal) while the schema carries no enum and only says 'The occasion (required)'. That enumeration is real added meaning at call time.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Specific verb+resource: 'Get curated outfit formulas for an occasion and weather', with an enumerated list of occasions. Clear what it produces, but nothing distinguishes it from the sibling what_to_wear_today, which sounds like the same job.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No when-to-use, when-not-to-use, or alternative routing. The sibling 'what_to_wear_today' overlaps heavily with this tool's stated purpose, and the description gives the agent no basis for choosing between them.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get a weather-aware outfit suggestion for today or tomorrow. Provide a city for live weather and forecast; optionally an occasion (casual, school, work, date, party, friends, formal). Asked in the evening? Use day=tomorrow — that's what people dress for.
| Name | Required | Description | Default |
|---|---|---|---|
| day | No | today = current conditions; tomorrow = full-day forecast with min/max and layering advice (default today) | |
| city | No | City for live weather (optional) | |
| occasion | No | One of: casual, school, work, date, party, friends, formal (optional, default casual) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, non-destructive, non-idempotent behavior, so the safety profile is covered. The description adds that live weather is fetched when a city is given (implying external/volatile data), but says nothing about output shape, latency, or missing-city fallback. Note the tension between 'live weather and forecast' and openWorldHint=false, though that is a closed-API interpretation and not a clear description-vs-annotation conflict.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three tight sentences, front-loaded with purpose before parameters and the timing tip. The inline re-listing of all seven occasion values duplicates the schema enum and is the one place words are spent without adding information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool is simple (3 optional params, read-only, no output schema), and the description covers purpose, the two-day scope, city behavior, and the default occasion. It leaves the returned suggestion format unspecified, which with no output schema is the main remaining gap.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the baseline is 3; the description goes slightly beyond by re-stating the occasion enum and, more valuably, giving the evening/tomorrow decision heuristic that makes the 'day' parameter actionable. The enum re-listing is redundant with the schema, but the heuristic earns the bump.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description gives a specific verb+resource ('Get a weather-aware outfit suggestion') and bounds scope to today/tomorrow, which is concrete. It never names or contrasts with the sibling 'suggest_outfit', so an agent cannot tell from the text alone why this differs from that tool.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It supplies a useful timing heuristic ('Asked in the evening? Use day=tomorrow') and notes city is for live weather, which is real guidance. However, it offers no tool-level routing: nothing tells the agent when to prefer this over 'suggest_outfit', and there are no exclusions or prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
about_outfitmakersuggest_outfitwhat_to_wear_todayVirtual try-on and on-model AI fashion photography: catalog search, try-on grids, HD delivery.
AI fashion design — product photos, videos, tech packs, colorways & fabric sims.
Manage your wardrobe or closet, discover ways to wear your clothes, and get outfit suggestions.
AI product photography for fashion sellers: Shopify photo audits, seasonal guides, AI try-on.
Add one secure layer between your agents and this server.
