Skip to main content
Glama
Sign In
Wolfe-Jam

mcp-context-card

by Wolfe-Jam
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Save Context Card

save_context_card
DestructiveIdempotent

Write the context card to context-card.html in the project and, when this server runs locally, open it in the person's browser.

Instructions

Write the context card to context-card.html in the project and, when this server runs locally, open it in the person's browser. Returns the card as Markdown (identity, AGENTS.md sections, memory, discovery) plus a clickable link to the saved file. Use this instead of pasting render_context_card's HTML into a chat that can't display it. Replaces any earlier context-card.html.

Input Schema

NameRequiredDescriptionDefault
openNoopen the saved card in the person's browser when the server runs locally (default: true)
themeNodefault: auto
accentNoCSS hex colour, e.g. #0066cc (default: the .fafa metadata.cards.accent, else black/white ink)
detailNothe Markdown reply: tldr (default) shows five facts, each cut short; full shows every fact whole. The saved file always has everything.
layoutNobusiness-card view (default: landscape)
expandedNorender every AGENTS.md section open (default: collapsed)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.7.1
    • changedInput schema / properties / accent / description
      Previous value: -"CSS hex colour, e.g. #FF702D (default: the AAIF palette)"New value: +"CSS hex colour, e.g. #0066cc (default: the .fafa metadata.cards.accent, else black/white ink)"
    • addedInput schema / properties / layout
      Added value: +{
+  "description": "business-card view (default: landscape)",
+  "enum": [
+    "landscape",
+    "portrait"
+  ],
+  "type": "string"
+}
  2. Addedv1.3.0

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true, idempotentHint=true and readOnlyHint=false, and the description reinforces the destructive aspect with 'Replaces any earlier context-card.html' and explains the conditional side effect (browser open only when the server is local). It doesn't add anything on the idempotency/rate-limit side beyond what annotations state, but it adds real context 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.

Conciseness4/5

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

Three sentences, front-loaded with the write action and side effect, then the return shape, then the alternatives and overwrite warning. Dense but no filler; the parenthetical content list is compact. Slightly overloaded for its length, but every clause earns its place.

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

Completeness5/5

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

With no output schema, the description carries the return-value burden and does so: Markdown containing identity, AGENTS.md sections, memory and discovery, plus a clickable file link. Combined with an explicit overwrite warning and no required parameters, an agent has everything needed to call it correctly.

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 100% and each parameter (open, theme, accent, detail, layout, expanded) is documented inline with defaults and enum meaning. The description's only added nuance is that 'the saved file always has everything' regardless of detail mode, which is already implied by the schema. Baseline 3 applies when the schema does the heavy lifting.

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

Purpose5/5

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

States a specific verb and artifact: writes the context card to context-card.html and optionally opens it in a browser. It also names the sibling it supersedes (render_context_card), so an agent can separate the two without reading either schema.

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

Usage Guidelines5/5

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

Gives an explicit routing rule: 'Use this instead of pasting render_context_card's HTML into a chat that can't display it.' That names the alternative and the condition that selects this tool, plus the local-server precondition for the browser side effect.

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

Deploy Server

Other Tools