Skip to main content
Glama
Sign In

A2UI Atomic Catalog

by ai.a2uicatalog
OverviewDiscussionsAdmin

sketch_agent_start

Start a real, live agent_sketchpad drawing: one Gemini call plans a complete picture as an ordered list of SVG strokes, the first stroke renders immediately, and the rest reveal as you call sketch_agent_poll again — a real multi-turn task, not a single one-shot render. MCP Apps hosts only (same as render_surface). Stateless server: the task is held in KV for 1 hour, not in this connection — keep the returned taskId and the next cursor to keep polling.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "subject": "<subject>"
    },
    "name": "sketch_agent_start"
  }
}

Input Schema

NameRequiredDescriptionDefault
subjectYesWhat to draw, e.g. "a lighthouse at sunset". Max 150 characters.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior5/5

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

Goes well beyond the annotations by disclosing that the server is stateless, that task state lives in KV for one hour rather than in the connection, and that the caller must retain the taskId and next cursor to keep polling. The 1-hour TTL and statelessness are the kind of operational facts an agent would otherwise discover only by failing.

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?

Dense but front-loaded: the core action comes first, then the progressive-render mechanic, then the host and state-retention caveats. It is somewhat long-winded in a single run-on construction, but nearly every clause carries information an agent needs.

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 still tells the agent what comes back (a taskId and next cursor) and what to do with it, plus the immediate first-stroke behavior. For a one-parameter, host-restricted, multi-turn tool, nothing material is missing.

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?

There is a single parameter, subject, and schema coverage is 100% with a description and length limit already in the schema. The tool description adds no extra meaning about subject format or constraints beyond what the schema provides, so the baseline applies.

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 resource — start a live agent_sketchpad drawing — and explains the mechanic: a Gemini call plans an ordered list of SVG strokes, the first renders immediately, the rest reveal via sketch_agent_poll. It explicitly distinguishes the tool from a single one-shot render, so an agent can tell what it is versus the poll sibling.

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

Usage Guidelines4/5

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

Gives clear operating context: it is for multi-turn progressive drawing, and continued use requires calling sketch_agent_poll with the returned taskId and cursor. It also names a real constraint (MCP Apps hosts only, same as render_surface). It stops short of stating an explicit when-not/alternative-tool condition, but the continuation path and host requirement are unambiguous.

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

All A2UI Atomic Catalog toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources