MaterialsCodeGraph

mcg_list_runs

Read-only

List runs, newest first: every run of this key's owner, or one quote's runs when quote_id is given. Returns at most limit rows (default 20, maximum 100). Each row carries state, spend_tokens, created_by_key_name (null when launched in the browser), study, headline (the AI brief's first line) and app_url. Returns runs and next_before: pass next_before as before to get the next older page; it is null on the last page.

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": "mcg_list_runs"
  }
}

Input Schema

Name	Required	Description
`limit`	No	Optional: rows per page, default 20.
`before`	No	Optional: a run_id from this listing (next_before of the previous page); returns only older runs.
`quote_id`	No	Optional: the quote_id (simulation) to list runs for.

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 28, 2026

addedInput schema / properties / before

Added value: +{
+  "description": "Optional: a run_id from this listing (next_before of the previous page); returns only older runs.",
+  "type": "string"
+}

addedInput schema / properties / limit

Added value: +{
+  "description": "Optional: rows per page, default 20.",
+  "maximum": 100,
+  "minimum": 1,
+  "type": "integer"
+}

First observedOct 8, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Beyond readOnlyHint=true, it discloses pagination mechanics (next_before becomes the next call's before, null on last page), the row cap (default 20, max 100), and per-row semantics including spend_tokens, state, and that created_by_key_name is null for browser-launched runs. That is meaningful behavioral context an agent cannot get from the annotations.

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?

Four sentences, each carrying distinct payload — scope, paging, row shape, continuation token — with scope front-loaded. No filler or repetition of the tool name.

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?

No output schema exists, yet the description compensates by enumerating the return envelope (runs plus next_before) and the key row fields. For a three-optional-parameter list tool, nothing needed to invoke or paginate it correctly is missing.

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

Parameters4/5

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

Schema coverage is 100%, so baseline is 3, but the description adds real meaning: limit is bounded at 100, before is tied explicitly to the previous response's next_before, and quote_id scopes to a simulation's runs. It goes past restating the schema by explaining how the parameters compose across pages.

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?

Names a specific verb and resource ('List runs') plus the exact scope: all runs for this key's owner, or a single quote's runs when quote_id is supplied. Ordering ('newest first') and per-row field set are stated, so an agent can distinguish it from mcg_get_run without opening a schema.

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?

Clearly states the condition that changes behavior: pass quote_id to narrow to one quote's runs, omit it to list everything for the owner. It does not explicitly route to siblings such as mcg_get_run for a single run or mcg_cancel_run for mutations, but the listing context is unambiguous.

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

All MaterialsCodeGraph 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.

Resources

Need Help?