code_call
Call a cell hosted in the sandbox: your own by name, or a community cell by cell (from...
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| cell | No | ||
| name | No | ||
| input | No |
Call a cell hosted in the sandbox: your own by name, or a community cell by cell (from...
| Name | Required | Description | Default |
|---|---|---|---|
| cell | No | ||
| name | No | ||
| input | No |
Changes observed during successful MCP inspections.
Input schema / properties / cell / descriptionRemoved value: -"a community cell, e.g. hello.echo"Input schema / properties / input / descriptionRemoved value: -"JSON value or string sent as one line"Input schema / properties / name / descriptionRemoved value: -"your cell's name: 1-32 of a-z, 0-9, -"Input schema / properties / cell / descriptionAdded value: +"a community cell, e.g. hello.echo"Input schema / properties / input / descriptionAdded value: +"JSON value or string sent as one line"Input schema / properties / name / descriptionAdded value: +"your cell's name: 1-32 of a-z, 0-9, -"Input schema / properties / cell / descriptionRemoved value: -"a community cell, e.g. hello.echo"Input schema / properties / input / descriptionRemoved value: -"JSON value or string sent as one line"Input schema / properties / name / descriptionRemoved value: -"your cell's name: 1-32 of a-z, 0-9, -"Input schema / properties / cell / descriptionAdded value: +"a community cell, e.g. hello.echo"Input schema / properties / input / descriptionAdded value: +"JSON value or string sent as one line"Input schema / properties / name / descriptionAdded value: +"your cell's name: 1-32 of a-z, 0-9, -"Input schema / properties / cell / descriptionRemoved value: -"a community cell, e.g. hello.echo"Input schema / properties / input / descriptionRemoved value: -"JSON value or string sent as one line"Input schema / properties / name / descriptionRemoved value: -"your cell's name: 1-32 of a-z, 0-9, -"Input schema / properties / cell / descriptionAdded value: +"a community cell, e.g. hello.echo"Input schema / properties / input / descriptionAdded value: +"JSON value or string sent as one line"Input schema / properties / name / descriptionAdded value: +"your cell's name: 1-32 of a-z, 0-9, -"Input schema / properties / cell / descriptionRemoved value: -"a community cell, e.g. hello.echo"Input schema / properties / input / descriptionRemoved value: -"JSON value or string sent as one line"Input schema / properties / name / descriptionRemoved value: -"your cell's name: 1-32 of a-z, 0-9, -"Input schema / properties / cell / descriptionAdded value: +"a community cell, e.g. hello.echo"Input schema / properties / input / descriptionAdded value: +"JSON value or string sent as one line"Input schema / properties / name / descriptionAdded value: +"your cell's name: 1-32 of a-z, 0-9, -"Input schema / properties / cell / propertiesRemoved value: -nullInput schema / properties / input / propertiesRemoved value: -nullInput schema / properties / name / propertiesRemoved value: -nullInput schema / properties / cell / descriptionRemoved value: -"a community cell, e.g. hello.echo"Input schema / properties / cell / propertiesAdded value: +nullInput schema / properties / input / descriptionRemoved value: -"JSON value or string sent as one line"Input schema / properties / input / propertiesAdded value: +nullInput schema / properties / name / descriptionRemoved value: -"your cell's name: 1-32 of a-z, 0-9, -"Input schema / properties / name / propertiesAdded value: +nullInput schema / properties / cellAdded value: +{
+ "description": "a community cell, e.g. hello.echo",
+ "type": "string"
+}Input schema / requiredRemoved value: -[
- "name"
-]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=false, openWorldHint=true, idempotentHint=false, destructiveHint=false, so the safety profile is covered structurally. The description adds only that execution happens in a sandbox; it does not address what calling a cell does, side effects, or failure modes — and it is truncated before any such detail could appear.
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?
What exists is compact and front-loads the key distinction, but the text is literally truncated mid-parenthetical, which is a structural defect rather than conciseness.
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?
For a 3-parameter, zero-coverage, no-output-schema tool with open-world behavior, the description should explain the `input` payload shape, what a cell invocation returns, and how it differs from `cell_call`. The truncated one-liner delivers none of this.
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 0%, so the description carries the burden. It does usefully contrast `name` (your own cell) against `cell` (community cell), which the bare schema does not convey. But the `input` parameter — presumably the argument payload — is never mentioned, and the sentence is incomplete.
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 verb+resource is specific ("Call a cell hosted in the sandbox"), and it hints at two modes of addressing a cell. But the sentence is cut off mid-clause and never distinguishes this from close siblings like `cell_call` or `run_code`, leaving the agent to guess.
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?
It implicitly gives a routing rule — use `name` for your own cell, `cell` for a community cell — which is real usage guidance. However the explanation trails off at "(from...", so the community-cell path is never fully explained and no when-not-to-use guidance is given relative to `cell_call`.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.