Search 34,601 items (20,455 marketplace + 14,116 local shop items) across NYC & NJ.
Scored across 3 tools
Each tool maps to a distinct layer: discovery (search_marketplace), single-record lookup (get_item_details), and aggregate analytics (get_price_report). The only mild overlap is pricing—get_item_details returns a verified price for one item while get_price_report returns medians/statistics—but the descriptions make the single-vs-aggregate boundary clear enough.
All three names follow a strict snake_case verb_noun pattern: get_item_details, get_price_report, search_marketplace. The prefixes are semantically meaningful (get = retrieve a known resource, search = discover), so the convention is both consistent and informative.
Three tools is at the low end but each earns its place and there is no redundancy—discovery, detail, and pricing are the natural minimal surface for a read-only marketplace data server. It is a touch thin, since a category/borough browse or category-listing tool would round out exploration without search keywords.
Search, item detail (which bundles photos, seller, neighborhood, and similar items), and market pricing cover the core read-only workflows with no obvious dead ends for an agent. Minor gaps: no standalone way to enumerate categories or boroughs/neighborhoods as facets, forcing an agent to guess valid filter values.
Get complete structured item details (photos, verified price, condition, seller, neighborhood, and similar available items) by Moonoh item ID or URL.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | Moonoh item ID (e.g. 'karrot-uh7b3dkne8ex', 'heykorean-674246') or Moonoh item URL | |
| url | No | Optional Moonoh item URL |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description carries the full burden. It does disclose the returned content (photos, verified price, condition, seller, neighborhood, similar items), which is the key behavioral fact for a read tool, but it says nothing about authentication, rate limits, or what happens with an invalid/expired ID.
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?
One sentence, zero waste, with the access method front-loaded. The parenthetical field list earns its space by defining the scope of 'complete details'.
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?
With no output schema and no annotations, the description correctly compensates by enumerating what is returned, which is what an agent needs before calling. Only error/invalid-ID behavior and the id-vs-url redundancy are left unaddressed.
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 both parameters are already documented, and the description's 'by Moonoh item ID or URL' merely mirrors that. It does not clarify the notable overlap where the required 'id' field also accepts a URL, nor when the separate optional 'url' parameter should be used instead.
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?
A specific verb ('Get') and resource ('complete structured item details') with the lookup key named (Moonoh item ID or URL), plus an enumerated field list that scopes what 'details' means. It is clearly distinct from search_marketplace in spirit, but never names or contrasts the siblings, so it stops short of a 5.
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?
Usage is only implied: the agent can infer this is the lookup to use once it already has an item ID or URL. There is no statement of when to prefer it over get_price_report (which also concerns price) or search_marketplace, and no prerequisites or failure conditions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get real-time pricing statistics, median prices, and category breakdowns across 34,601 items (20,455 marketplace listings + 14,116 local shop items) in NYC boroughs and Northern NJ.
| Name | Required | Description | Default |
|---|---|---|---|
| region | No | Region name ('manhattan', 'brooklyn', 'queens', 'flushing', 'bayside', 'astoria', 'bronx', 'staten-island', 'bergen-county-nj', 'hudson-county-nj', 'all') |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description bears the full burden. It usefully discloses dataset composition (marketplace vs local shop items) and geographic scope, and 'Get' implies a read operation. However, it says nothing about freshness/caching, whether aggregation is over active listings, or cost/latency characteristics of a 34k-item scan.
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 front-loaded sentence that leads with the core action and output content. The counts (34,601 / 20,455 / 14,116) are slightly heavy but legitimately calibrate the dataset's trustworthiness and coverage.
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?
No output schema and no annotations, so the description must cover more. It names the report contents (median prices, category breakdowns) but doesn't explain how results are grouped or structured, what 'all' returns, or how regions map to rows — gaps an agent would hit when interpreting the response.
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% and the single region parameter is fully enumerated in the schema, so the description needn't restate it. It adds only indirect meaning by naming the covered boroughs/counties, which corroborates but does not extend the schema. Baseline 3 is appropriate.
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?
States a specific verb and resource ('Get real-time pricing statistics, median prices, and category breakdowns') plus a precise data scope (34,601 items across NYC boroughs and Northern NJ). This is clearly an aggregate price-analytics tool, distinct from get_item_details (single item) and search_marketplace (listing search).
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 explicit guidance on when to use this versus get_item_details or search_marketplace, nor on prerequisites or exclusions. The usage is only implied by the scope description (aggregate pricing research).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search 34,601 items (20,455 marketplace listings + 14,116 local shop items) in NYC & Northern NJ by keyword, category, or borough.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum number of results to return (default 15, max 50) | |
| query | No | Search term or item name (e.g. 'dining table', 'tiffany bracelet', 'sofa', 'airpods', 'puffer jacket') | |
| borough | No | Geographic filter ('manhattan', 'brooklyn', 'queens', 'bronx', 'staten-island', 'bergen-county-nj', 'hudson-county-nj', 'all') | |
| category | No | Category filter ('furniture', 'fashion', 'electronics', 'baby & kids', 'sports', 'food & groceries', 'all') |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden. It usefully discloses dataset composition and geographic scope, but omits return format, sorting, and pagination behavior beyond what the limit schema says.
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 front-loaded sentence that states the action, scope, and filters with no wasted text. The counts are informative rather than bloated.
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 four-parameter read-only search with no output schema or annotations, the description covers data scope and filtering dimensions. It leaves result shape, ordering, and pagination behavior unspecified.
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 description coverage is 100% and all four parameters are documented in the schema. The description reinforces keyword/category/borough as search dimensions but adds no syntax or format details beyond the schema, so baseline 3 applies.
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?
States a specific verb ('Search') and resource ('items'), with dataset counts and geographic/facet scope. It does not explicitly differentiate from siblings like get_item_details or get_price_report, but the search purpose is clear.
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?
The description implies discovery usage by listing keyword, category, and borough filters, but gives no explicit when-to-use guidance versus get_item_details or get_price_report, and no exclusions.
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.
get_item_detailsget_price_reportsearch_marketplaceRead-only catalog for Green Gooding — NYC peer-to-peer rental marketplace.
Sold comps and active listings from eBay, Poshmark, Mercari, Depop, Vinted, TCGplayer and more.
Search and shop curated second-hand design: furniture, lighting, art and designer bags.
Search and explore taste-led finds in clothing, audio, designed objects and music.
Add one secure layer between your agents and this server.
