Search artist-credited art prints and canvas by artwork title, artist, or subject, with sizes, finishes, and artwork links. Request a print on Image Kind’s website; the studio confirms price and shipping before payment, and the MCP does not generate images, place orders, or access customer accounts.
Scored across 2 tools
find_prints is clearly for discovery via title/artist/subject search, while get_prints is for direct retrieval by id. The two tools have distinct, non-overlapping purposes.
Both tools follow a consistent verb_noun snake_case pattern (find_prints, get_prints) with the same noun, making the set predictable.
Two tools is on the thin side for a catalog server, though they cover the core read operations. The rubric treats 1-2 tools as borderline.
The read-only catalog is well-covered with search and retrieval by id, but minor gaps like bulk listing or pagination are absent. For the stated scope, it is largely complete.
Search Image Kind’s starting collection by artwork title, artist or subject. Returns real artwork pages, artist credits, sizes and finishes. All listed works are available to print to order. Prices and shipping require studio confirmation. This reads the catalog; it does not place an order or take payment.
Returns a catalog id. No background work is started.
| Name | Required | Description | Default |
|---|---|---|---|
| query | No | An artwork title, artist, subject, or empty for the collection. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare read-only, idempotent, non-destructive and non-open-world. The description adds genuinely useful context beyond them: it does not place an order or take payment, and no background work is started, which clarifies side-effect scope for an agent.
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?
Front-loaded with the core action and searchable facets, then boundaries. Slightly repetitive in the closing lines (read-only and no-background-work restate the same non-mutation idea), but no sentence is wasted.
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 compensates by stating the return (a catalog id) and the nature of results (artwork pages, artist credits, sizes, finishes). Only the relationship to the sibling get_prints is missing.
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 there is a single optional parameter already documented with its facets and empty-means-whole-collection behavior. The description mentions the same facets, so it adds little beyond the schema; 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 (search the starting collection) plus the searchable facets (title, artist, subject). It never contrasts itself against the sibling get_prints, so an agent cannot tell from the description alone which of the two to pick.
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?
Implies when to use it by naming the searchable dimensions, and sets a boundary that prices/shipping need studio confirmation. However, there is no explicit when-not guidance or routing to the sibling get_prints, leaving selection to inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Retrieve the public art prints catalog entry by id. Returns the entry as text and its link on Image Kind's site. An unknown id returns an error.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | The catalog id returned by find_prints. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuine value beyond that: it discloses the return shape (entry as text plus its Image Kind site link) and the failure mode (unknown id returns an error), which the annotations cannot convey.
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 short sentences with zero filler, and the core action is front-loaded before the return and error details. Every sentence carries information an agent needs.
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 one-parameter read tool with no output schema, the description covers the essential gaps: what comes back (text plus link) and what failure looks like (error on unknown id). Only the exact error payload or pagination-style concerns are unaddressed, which is minor here.
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 the single id parameter is already documented there as the catalog id returned by find_prints. The description adds only "by id" with no format, length, or example detail beyond the schema, 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: "Retrieve the public art prints catalog entry by id." The id-based lookup implicitly distinguishes it from the search-oriented sibling find_prints, but the description never names that sibling explicitly, so differentiation is left partly to inference.
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 implied rather than stated: the tool is used once you have a catalog id, and the schema notes the id comes from find_prints. There is no explicit when-to-use vs find_prints statement, but two useful boundary facts are given (unknown id errors, returns the site link), which raises it above pure boilerplate.
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.
find_printsget_prints
Add one secure layer between your agents and this server.