Inject block scripts into mBlock, execute the hat block, and retrieve a variable's value in a single call.
LIVE combo (like upload-and-monitor): inject a script, run its hat, then read back a variable — new blocks to visible result in one call.
| Name | Required | Description | Default |
|---|---|---|---|
| x | No | ||
| y | No | ||
| blocks | Yes | ||
| target | No | Sprite1 | |
| readVar | No | Variable to read back after running | |
| hatOpcode | No | event_whenflagclicked |
Changes observed during successful MCP inspections.
v1.0.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=false, destructiveHint=false, and idempotentHint=true, covering the safety profile. The description adds that this is a combination of mutation (inject and run) and a read (variable retrieval), which is consistent. It does not contradict annotations and provides useful context about the multi-step nature.
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 description is a single, dense sentence that front-loads the core purpose and avoids fluff. It is concise and immediately conveys the tool's unique value proposition without unnecessary detail.
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?
With six parameters, a recursive blocks schema, and no output schema, the description is insufficient. It does not mention the return value (presumably the variable value), nor does it clarify the meaning of positional parameters like target, x, and y. An agent would need to inspect the schema and likely infer usage from sibling tools, which is not ideal for a tool that combines multiple operations.
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 only 17%, with only readVar described. The tool description mentions 'inject a script, run its hat, read back a variable', which loosely maps to blocks, hatOpcode, and readVar, but does not explain parameters like x, y, or target. The description fails to compensate for the low schema coverage, leaving these parameters underspecified.
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 composite action: inject a script, run its hat, and read back a variable, all in one call. It uses the analogy 'like upload-and-monitor' and explicitly mentions the three sub-steps, clearly distinguishing it from sibling tools like app_put_script, app_run_hat, and app_get_var.
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 phrase 'LIVE combo' and 'in one call' conveys that this is a convenience wrapper for combined operations. It implies an agent should use this tool when it needs the full pipeline, but it does not explicitly state when to use alternatives instead, though the sibling names make that inferable.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.