mcp-chat-cards

by jhauga

Overview Schema Source Related Servers Discussions Admin

TypeScript

Local

Create table card

create_table_card

Render an HTML table card from row data or raw text, auto-detecting delimiters and turning URL cells into links.

Instructions

Render an HTML table card from explicit rows, or convert loosely delimited text into a balanced table (delimiter auto-detected; newlines can mark cells). URL cells become links.

Input Schema

TableJSON Schema

Name	Required	Description
`rows`	No	Explicit cell data, row-major
`text`	No	Raw text to convert when rows are not given
`title`	Yes
`caption`	No
`columns`	No
`headers`	No	Column titles; padded if fewer than columns
`subtitle`	No
`tutorTerms`	No	Educational tutor terms. The first occurrence of each term in the card's visible prose is underlined; hovering ~1.2s shows the tip and notifies the host so the model can follow up. Terms are matched once per card, longest first, and never inside code samples, tooltips, or another term's tip. Matching is CASE-SENSITIVE, so "PATH" does not attach its tip to a filesystem "path"; set caseInsensitive on a term to match any casing. Term and tip are PLAIN text.
`linkColumns`	No
`cellDelimiter`	No
`contextActions`	No	Right-click menu actions the model anticipates being useful. Choosing one sends its prompt to the conversation; use {{selection}} to include the user's selected text.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`card`	Yes
`parts`	Yes	Split state, present on EVERY card result so one completeness check works for all card types. Cards that cannot split always report {current:1,total:1,hasMore:false}; create_markdown_card and create_code_tour_card pack oversized content into parts and can report more. Read hasMore rather than the card title to decide whether content was withheld.

Schema Changelog

Changes observed during successful MCP inspections.

Changed6 schema fields changedv0.1.3-alphaAug 21, 2026

removedInput schema / $schema

Removed value: -"http://json-schema.org/draft-07/schema#"

changedInput schema / properties / tutorTerms / description

Previous value: -"Educational tutor terms. The first occurrence of each term in the card's visible prose is underlined; hovering ~1.2s shows the tip and notifies the host so the model can follow up. Terms are matched once per card, longest first, and never inside code samples, tooltips, or another term's tip. Term and tip are PLAIN text."New value: +"Educational tutor terms. The first occurrence of each term in the card's visible prose is underlined; hovering ~1.2s shows the tip and notifies the host so the model can follow up. Terms are matched once per card, longest first, and never inside code samples, tooltips, or another term's tip. Matching is CASE-SENSITIVE, so \"PATH\" does not attach its tip to a filesystem \"path\"; set caseInsensitive on a term to match any casing. Term and tip are PLAIN text."

addedInput schema / properties / tutorTerms / items / properties / caseInsensitive

Added value: +{
+  "description": "Match the term regardless of letter case (default false)",
+  "type": "boolean"
+}

removedOutput schema / $schema

Removed value: -"http://json-schema.org/draft-07/schema#"

addedOutput schema / properties / parts

Added value: +{
+  "additionalProperties": false,
+  "description": "Split state, present on EVERY card result so one completeness check works for all card types. Cards that cannot split always report {current:1,total:1,hasMore:false}; create_markdown_card and create_code_tour_card pack oversized content into parts and can report more. Read hasMore rather than the card title to decide whether content was withheld.",
+  "properties": {
+    "current": {
+      "description": "Part number this result rendered (1-based)",
+      "type": "number"
+    },
+    "hasMore": {
+      "description": "True when content was withheld; call again with part: current + 1",
+      "type": "boolean"
+    },
+    "total": {
+      "description": "How many parts the content splits into",
+      "type": "number"
+    }
+  },
+  "required": [
+    "current",
+    "total",
+    "hasMore"
+  ],
+  "type": "object"
+}

changedOutput schema / required

Previous value: -[
-  "card"
-]New value: +[
+  "card",
+  "parts"
+]

Changed1 schema field changedv0.1.1-alphaAug 12, 2026

changedInput schema / properties / tutorTerms / description

Previous value: -"Educational tutor terms. Occurrences in the card are underlined; hovering ~1.2s shows the tip and notifies the host so the model can follow up."New value: +"Educational tutor terms. The first occurrence of each term in the card's visible prose is underlined; hovering ~1.2s shows the tip and notifies the host so the model can follow up. Terms are matched once per card, longest first, and never inside code samples, tooltips, or another term's tip. Term and tip are PLAIN text."

First observedv0.0.0-alphaAug 10, 2026

TDQS

A3.5/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description bears the full burden for behavior. It discloses useful behaviors: delimiter auto-detection, newlines as optional cell markers, and URL cells becoming links. It also implies a balanced table normalization. Yet it does not mention behavior for when both rows and text are supplied, or any failure modes, making it sufficient but not rich.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences, front-loaded with the core purpose and then adds a single behavioral detail (URL links). It is efficient, with no redundant fluff, and every clause adds a distinct use-case or behavior. This is an example of concise, high-value prose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 11 parameters and one required field (title), the description covers two main input modes but does not touch on caption, subtitle, columns, headers, tutorTerms, contextActions, or linkColumns. Though output schema exists, the set of options is broad, and many are left to the schema's implicit meaning. For an agent to use all features correctly, more explanation would be needed, but it suffices for the common path.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 45%, and several parameters (columns, caption, subtitle, linkColumns, cellDelimiter) lack inline descriptions. The description adds meaning for text and cellDelimiter (auto-detected) and linkColumns (URL cells become links), but it ignores caption, columns, subtitle, and headers beyond what is in the schema. It compensates for some gaps but not the majority, so it meets the minimum but not more.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Render an HTML table card from explicit rows, or convert loosely delimited text into a balanced table.' This is a specific verb plus resource, making it distinct from sibling creation tools like create_chart_card or create_form_card. The two modes (explicit rows vs. text) are named, adding specificity, though it doesn't explicitly name a different sibling or exclusion.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies two main use cases (structured rows or raw text conversion) and mentions auto-detection of delimiters, which gives some guidance. However, it does not explicitly state when to favor this over sibling card creators (e.g., for tabular data vs. charts) or provide any 'when not to use' guidance. Since siblings are numerous, a clearer routing could be expected, but the core instruction ('from explicit rows or text') is implied enough for basic use.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.