Ground-truth authentic photography and computer vision datasets catalog by Henry St John.
Scored across 2 tools
The two tools have clearly distinct purposes: one lists digital product catalogs (datasets, art packs, wallpapers), the other searches authentic photographs. There is no overlap in resource or action, so an agent can easily select the right tool.
Both names follow a consistent snake_case verb_noun pattern: list_all_datasets_and_packs and search_authentic_photos. The convention is predictable and readable throughout.
Two tools is borderline thin for a server that covers a dataset catalog, art packs, wallpapers, and a photo search across 195 categories. More granular tools (e.g., dataset search, detail retrieval) would better match the apparent scope.
The surface is missing key operations: no filtering or searching within datasets/packs, no retrieval of details for a specific dataset or pack, and no separate checkout flow beyond embedded URLs. Agents will hit dead ends for common marketplace tasks.
Lists all 50 Computer Vision training datasets, 10 Samsung The Frame Art TV packs, and 10 4K Wallpaper packs with EUR pricing and 1-click Stripe checkout URLs.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations at all, the description carries the full behavioral burden. It does disclose useful traits: the listing is exhaustive (fixed counts of 50/10/10), prices are in EUR, and results include 1-click Stripe checkout URLs, which tells the agent the payload is commercially actionable. It omits anything about auth requirements, whether the list is static or dynamic, pagination, or response shape.
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 with the verb and scope first, followed by the catalog contents and payment details. Nothing is redundant, though the explicit counts (50/10/10) read slightly as promotional padding rather than agent-critical 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?
With no output schema and no annotations, the description must carry full context. It partially compensates by naming EUR pricing and Stripe checkout URLs, but it does not describe the return structure, ordering, or how it relates to the sibling search tool, leaving meaningful gaps for a zero-argument listing endpoint.
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 there is nothing to misinterpret and the description adds no contradictory parameter claims. Baseline 4 applies for a no-parameter tool.
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 (Lists) and enumerates the exact resources returned, including their counts and the fact that pricing and checkout URLs are included. An agent immediately knows this is the catalog-listing endpoint. It never mentions the sibling search_authentic_photos, so the differentiation from alternatives is left implicit.
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 only describes what will be returned; it gives no guidance on when to call this versus search_authentic_photos, no precondition (e.g. for browsing/purchasing the full catalog), and no exclusions. The Stripe checkout detail hints at a purchase/browse scenario, but that is inference rather than stated guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Searches authentic, human-captured photographs with verified GPS and time telemetry across 195 thematic categories. Returns watermarked preview and 1-click direct_buy_url. Never exposes uncompressed originals.
| Name | Required | Description | Default |
|---|---|---|---|
| q | Yes | Subject, city, landmark, or concept (e.g. 'Tokyo rain neon', 'Swiss alpine train', 'Quebec autumn forest', 'laminites rocks') | |
| limit | No | Number of results to return (default 10, max 30) | |
| category | No | Optional category (e.g. 'Transport', 'Architecture', 'Nature', 'Animaux') |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description carries the full behavioral burden. It does disclose meaningful return-side traits — watermarked previews, a 1-click direct_buy_url, and that uncompressed originals are never exposed — but omits licensing/auth requirements, rate limits, and pagination behavior.
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 compact sentences with no filler, and the core capability plus its key differentiators are front-loaded. Minor redundancy between the 'authentic human-captured' framing and the telemetry claim, but overall tight.
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, the description usefully summarizes returns (preview plus buy URL). However, it lacks selection guidance versus the sibling tool and operational details (auth, limits), so it is adequate but not fully complete.
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%, so all three parameters (q, limit, category) are already documented in the schema. The description adds no syntax, format, or constraint details beyond that, so the 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 and resource (searches authentic, human-captured photographs) and adds distinguishing scope: verified GPS/time telemetry and 195 thematic categories. It is clearly a photo-search tool, but it never names or contrasts against its only sibling, list_all_datasets_and_packs.
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 explicit when-to-use guidance, prerequisites, or alternatives are given. The intended usage is only implied by the verb 'searches', leaving the agent to infer when this is preferred over the sibling dataset-listing tool.
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.
list_all_datasets_and_packssearch_authentic_photosHardscapeDesk: the site's own MCP server — dataset; every answer cites the site.
PunchListWorks: the site's own MCP server — dataset; every answer cites the site.
HeadcountDesk: the site's own MCP server — dataset; every answer cites the site.
Stocktaka: the site's own MCP server — dataset; every answer cites the site.
Add one secure layer between your agents and this server.
