@wrtnlabs/calculator-mcp
[ tools: 6 ][ checks: 11 ][ latency: 4ms ]
71/100(C)
npx -y @wrtnlabs/calculator-mcp
check breakdown
✓Tools exposed — Server exposed 6 tools.
• add
• div
• mod
• mul
• sqrt
• sub
✓Input schemas valid — All tools have a valid JSON-Schema input definition.
!Input schema quality — 11 schema-quality issue(s) across 6 tool(s).
add.a: parameter has no description
add.b: parameter has no description
div.a: parameter has no description
div.b: parameter has no description
mod.a: parameter has no description
mod.b: parameter has no description
mul.a: parameter has no description
mul.b: parameter has no description
sqrt.a: parameter has no description
sub.a: parameter has no description
sub.b: parameter has no description
→ Declare `required` for every schema that has properties, so agents know which params are mandatory.
→ Give every property a `description` and a concrete `type` (avoid bare `{}` placeholders).
!Output schemas — No tools declare an outputSchema.
→ Optional: declare outputSchema for tools with structured results so agents can validate/parse output reliably.
✓Duplicate tool names — All tool names are unique.
✓Tool naming — All tool names use spec-legal characters.
!Descriptions — 11 description issue(s) found.
add.a: parameter has no description
add.b: parameter has no description
div.a: parameter has no description
div.b: parameter has no description
mod.a: parameter has no description
mod.b: parameter has no description
mul.a: parameter has no description
mul.b: parameter has no description
sqrt.a: parameter has no description
sub.a: parameter has no description
sub.b: parameter has no description
→ Descriptions are the model's only guide to when/how to call a tool — treat them as prompt engineering.
→ Describe every tool and every parameter, including units, formats, and constraints.
→ Each tool's description should say something the name doesn't, and should be unique to that tool.
!Tool annotations — Annotation coverage 0% (0/30 hint fields set).
• add: no annotations at all
• div: no annotations at all
• mod: no annotations at all
• mul: no annotations at all
• sqrt: no annotations at all
• sub: no annotations at all
→ Add annotations: title, readOnlyHint, destructiveHint, idempotentHint, openWorldHint.
→ These let clients gate risky calls and give agents/users a friendly display name — optional but valuable.
!Tool titles — 6 of 6 tool(s) have no title.
• add: no top-level title (or annotations.title)
• div: no top-level title (or annotations.title)
• mod: no top-level title (or annotations.title)
• mul: no top-level title (or annotations.title)
• sqrt: no top-level title (or annotations.title)
• sub: no top-level title (or annotations.title)
→ Declare a top-level `title` on each tool — it gives clients a friendly display name distinct from the machine-readable `name`.
→ `annotations.title` (the older location) is also accepted, but the top-level `title` field is now the spec-preferred place for it.
!Server instructions — No top-level instructions declared.
→ Declare instructions to guide agents on when/how to use this server.
→ Return a non-empty `instructions` string in your InitializeResult — most SDKs let you set this alongside serverInfo.
✓Handshake + list latency — tools/list responded in 4ms.
add the badge
Paste into your README:
[](https://scoremcp.dev/servers/mcp-server-calculator)