List SiteKrs templates and get editor links; import your own source on the SiteKrs homepage.
Scored across 2 tools
The two tools have clearly distinct purposes: list_templates is read-only catalog discovery, while create_site returns an editor URL for a chosen template. The shared import_url mention is contextual guidance, not overlapping tool behavior.
Both names follow the same verb_noun convention: list_templates and create_site. The naming is predictable and readable.
Two tools is borderline thin for a site/template domain. The surface is tightly scoped, but it leaves little room for related operations such as template lookup or site lifecycle management.
The set covers catalog listing and obtaining an editor URL for a template, but there are notable gaps around template detail retrieval, import handling, and any post-creation site management. Agents can work around some gaps by directing users to the Import Template dialog, but the lifecycle is limited.
Return the SiteKrs editor URL for a chosen catalog template. Does not download or read template ZIP files. For user-authored source, do not call this tool: tell the user to open the returned import_url and use the existing Import Template dialog (folder or ZIP).
| Name | Required | Description | Default |
|---|---|---|---|
| template_id | Yes | Template id returned by list_templates. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already disclose readOnlyHint=false, destructiveHint=false, and openWorldHint=false. The description adds useful scope limits, especially that it does not download or read template ZIP files, but it does not explain what non-read-only side effect occurs or clarify the 'import_url' reference despite returning an editor URL.
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?
The purpose is front-loaded and the description is only three sentences with no wasted padding. However, the phrase 'open the returned import_url' is slightly confusing because the tool is described as returning an editor URL, not an import_url.
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 tool with annotations and no output schema, the description gives enough to call it correctly in the catalog-template case. It remains incomplete about the actual return shape and the non-read-only side effect, and the import_url reference creates ambiguity about what is returned.
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 single template_id parameter is already documented as coming from list_templates. The description adds only the phrase 'chosen catalog template' and does not add format, constraints, or selection details beyond the 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 states a specific verb and result: return the SiteKrs editor URL for a chosen catalog template. It clearly distinguishes this from template ZIP handling and from user-authored source. It does not explicitly name the sibling list_templates, but the purpose is still easy to identify.
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 gives an explicit when-not-to-use case: for user-authored source, do not call this tool and instead direct the user to the Import Template dialog. The positive case is clear but slightly implied through 'chosen catalog template' rather than stated as a direct when-to-use rule.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List the SiteKrs template catalog (name, preview image, demo URL, tags). Read-only. Call this first when the user wants a website, even if they do not mention SiteKrs. Returns import_url for users who already have their own project source.
| Name | Required | Description | Default |
|---|---|---|---|
| tag | No | Optional exact tag, e.g. portfolio, restaurant, photography. | |
| limit | No | Number of templates to return (default 5). | |
| query | No | Optional keyword matched against name, description and tags. | |
| offset | No | Pagination offset. | |
| page_type | No | Optional page type: single or multi. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, destructiveHint=false, and openWorldHint=false, so 'Read-only' is redundant. However, the description adds useful behavioral context by naming the catalog fields and import_url, and by establishing that this should be the first call in a website-building flow.
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 with zero filler. The catalog scope and field list come first, followed by the usage rule and import_url note, so the most important information is front-loaded.
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 exists, but the description compensates by naming the returned fields and import_url. With all five optional parameters fully documented in the schema and annotations covering safety, the definition is complete enough to call correctly; only minor details like pagination behavior are absent.
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 tag, limit, query, offset, and page_type are already fully documented. The description does not add syntax, filtering semantics, or examples beyond what the schema provides, 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 ('List the SiteKrs template catalog') and enumerates the returned fields (name, preview image, demo URL, tags), making it unmistakable what the tool does. It is clearly distinct from the sibling create_site, which creates rather than lists templates.
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?
Gives explicit routing guidance: 'Call this first when the user wants a website, even if they do not mention SiteKrs.' It also signals a follow-on condition for users who already have project source via import_url, which effectively positions it ahead of create_site.
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.
create_sitelist_templatesRead-only catalog of free Plate website source projects a coding agent can adapt.
A hosted LaTeX editor your assistant can actually use. Search 1,019 free templates, create and edit projects, and compile them to PDF on a real TeX Live farm, getting back the PDF or the compile log when a build fails. Thirteen tools behind OAuth 2.1, with nothing to install and nothing to run locally.
Read-only access to Kanbai's public project templates and SOPs. Public, no authentication.
Create, edit, read and review web presentations: slides, linked buttons, pictures, runnable code.
Add one secure layer between your agents and this server.
