Picodev Lab

Push sources to the editor

push_to_editor

Replace the code in the human's browser and, if run, compile it in the lab's cloud and start it. The fallback of push_program: use it only when the toolchain to compile locally is missing (no arduino-cli, core or library).

Input Schema

Name	Required	Description	Default
`run`	No
`files`	Yes
`session`	No
`agent_token`	No

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed7 schema fields changedOct 23, 2026
- addedInput schema / properties / agent_token / anyOf
```
Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]
```
- addedInput schema / properties / agent_token / default
```
Added value: +null
```
- removedInput schema / properties / agent_token / type
```
Removed value: -"string"
```
- addedInput schema / properties / session / anyOf
```
Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]
```
- addedInput schema / properties / session / default
```
Added value: +null
```
- removedInput schema / properties / session / type
```
Removed value: -"string"
```
- changedInput schema / required
```
Previous value: -[
-  "session",
-  "agent_token",
-  "files"
-]New value: +[
+  "files"
+]
```
First observedOct 21, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations declare readOnlyHint=false and destructiveHint=false; the description adds real behavioral context beyond them - it overwrites the human's editor buffer, may compile in the lab's cloud, and may start execution. It leaves the default of `run=true` and the meaning of the session/token fields implicit, and does not flag that replacing browser code discards prior content.

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?

Two sentences, front-loaded with the primary action and closed with the routing rule, with no filler. Every clause conveys either what it does or when to pick it.

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?

An output schema exists, so return values need not be described, and the routing guidance is solid. But with four parameters at 0% schema coverage and mutation semantics, the description is thin on the mechanics of the `files`, `session`, and `agent_token` inputs.

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

Parameters2/5

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

Schema description coverage is 0%, so the description carries the full burden, yet it only hints at `run` ('if run') and says nothing about the `files` array shape, `session`, or `agent_token`. An agent cannot infer from the description what a session identifier means or when to supply the token.

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 - 'Replace the code in the human's browser' - and then names the sibling push_program as the default, positioning itself as the fallback. An agent can distinguish it from push_program and push_circuit without opening any 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 conditional: 'use it only when the toolchain to compile locally is missing (no arduino-cli, core or library)'. Both the when and the when-not are stated, along with the alternative that should be preferred otherwise.

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

All Picodev Lab tools Inspect

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.