run402-mcp

Overview Schema Source Related Servers Discussions Admin

docs

Look up the SDK reference for run snippets: fetch the namespace table, a specific section, or search sections by keyword to find matching API details.

Instructions

The SDK reference for run snippets, from the copy shipped in this package, so it matches the SDK the snippet runs against. No arguments: the run primer, the r namespace table, and the topics. topic: one namespace or section (assets, project.apply, rooms, local-state) or sdk for all of it; search: sections containing every word. Long answers are a window plus a ref for expand_result. Any other operation is a run snippet against r, the Node SDK client; docs is its reference.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "docs"
  }
}

Input Schema

Name	Required	Description	Default
`topic`	No	`index` (default: the run primer, the r namespace table, the topics), `sdk` (the whole SDK reference), or one section: a namespace such as `projects`, `assets`, `project.apply`, `rooms`, or a section slug from the index.
`search`	No	Words to look for; returns up to 8 SDK reference sections whose heading or body contain all of them.

Output Schema

Name	Required	Description	Default
`ref`	No
`kind`	No
`error`	No
`lines`	No
`shown`	No
`total`	No
`status`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedv4.126.1Oct 22, 2026

addedOutput schema / properties / error / properties / diagnostics

Added value: +{
+  "items": {
+    "additionalProperties": true,
+    "properties": {
+      "code": {
+        "type": "string"
+      },
+      "column": {
+        "type": "integer"
+      },
+      "line": {
+        "type": "integer"
+      },
+      "message": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "line",
+      "column",
+      "code",
+      "message"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}

addedOutput schema / properties / error / properties / diagnostics_ref
```
Added value: +{
+  "type": "string"
+}
```
addedOutput schema / properties / error / properties / diagnostics_total
```
Added value: +{
+  "type": "integer"
+}
```

AddedSep 25, 2026

TDQS

A3.6/5.0

Behavior4/5

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

With no annotations, the description carries the burden and does add real context: default behavior with no arguments, that long answers come back as a window plus a ref for expand_result, and that results are scoped to the packaged copy. It still omits whether the tool is strictly read-only and any size/rate limits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

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

Purpose is front-loaded, but the body is a semicolon-chained run-on mixing return behavior, parameter semantics, and sibling routing in one paragraph. The trailing sentence about 'any other operation is a run snippet' is confusingly placed and reads as an afterthought.

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

Completeness4/5

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

An output schema exists, so return shapes needn't be explained, yet the description usefully adds the windowing/expand_result behavior. For a two-optional-param reference lookup, an agent has enough to call it correctly, though the absence of any explicit 'when to call' leaves a small gap.

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 coverage is 100%, so the baseline is 3. The description adds a little beyond the schema — naming `local-state` and framing `search` as matching every word — but largely restates what the schema already documents for `topic` and `search`.

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

Purpose4/5

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

The first sentence names a specific resource (the SDK reference for `run` snippets) and its provenance (shipped with the package so it matches the runtime). The closing clause explicitly separates it from sibling `run` ('Any other operation is a `run` snippet against `r`; `docs` is its reference'). The verb is implicit ('look up reference') rather than stated, which keeps it below a 5.

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

Usage Guidelines3/5

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

Usage is described only structurally — what no arguments returns, what `topic` selects, what `search` matches — rather than when to prefer this tool over `run` or `expand_result`. The expand_result handoff is mentioned but the condition ('long answers') is vague. The agent can infer 'consult docs before writing a run snippet' but it is never stated.

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

Deploy Server