Skip to main content
Glama
collapseindex

CI-1T Prediction Stability Engine

fleet_session_round

Submit a scoring round to evaluate per-node scores and retrieve the cumulative fleet snapshot for monitoring fleet drift and prediction stability.

Instructions

Submit a scoring round to an existing fleet session. Each node's scores array is evaluated and the cumulative fleet snapshot is returned. Response: { round, nodes: [{ episodes: [...] }], fleet_summary }. Episodes in the response can be passed to visualize, alert_check, or compare_windows.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
session_idYesFleet session ID
scoresYesPer-node score arrays for this round. Max 16 nodes, 10,000 scores per node.

Implementation Reference

  • src/index.ts:632-649 (registration)
    Registration of the 'fleet_session_round' tool via server.tool(), defining its name, description, input schema (session_id and scores), and the async handler callback.
    server.tool(
      "fleet_session_round",
      "Submit a scoring round to an existing fleet session. Each node's scores array is evaluated and the cumulative fleet snapshot is returned. Response: { round, nodes: [{ episodes: [...] }], fleet_summary }. Episodes in the response can be passed to visualize, alert_check, or compare_windows.",
      {
        session_id: z.string().describe("Fleet session ID"),
        scores: z.array(z.array(z.number().int().min(0).max(65535)).min(1).max(10000)).min(1).max(16).describe("Per-node score arrays for this round. Max 16 nodes, 10,000 scores per node."),
      },
      async ({ session_id, scores }) => {
        const guard = requireApiKey();
        if (guard) return guard;
        const result = await apiFetch("/api/fleet-session", {
          method: "POST",
          headers: apiKeyHeaders(),
          body: { action: "round", session_id, scores },
        });
        return formatResult(result);
      }
    );
  • Input schema for fleet_session_round: session_id (string) and scores (array of arrays of Q0.16 integers, 1-16 nodes, 1-10000 scores each).
      session_id: z.string().describe("Fleet session ID"),
      scores: z.array(z.array(z.number().int().min(0).max(65535)).min(1).max(10000)).min(1).max(16).describe("Per-node score arrays for this round. Max 16 nodes, 10,000 scores per node."),
    },
  • Handler logic: checks API key authentication, then POSTs to /api/fleet-session with action: 'round', session_id, and scores. Returns the API response formatted as MCP text content.
    async ({ session_id, scores }) => {
      const guard = requireApiKey();
      if (guard) return guard;
      const result = await apiFetch("/api/fleet-session", {
        method: "POST",
        headers: apiKeyHeaders(),
        body: { action: "round", session_id, scores },
      });
      return formatResult(result);
    }
Behavior3/5

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

The description discloses the core behavior (submits scores, evaluates, returns snapshot) and response structure, making it minimally adequate. However, without annotations, it does not mention potential side effects, error conditions, or auth requirements.

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?

The description is concise (two sentences) and well-structured: first sentence states action and mechanism, second defines response shape and downstream connections. No unnecessary words.

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?

Given the tool's simplicity (2 required params, no output schema), the description provides sufficient context for use, including the response structure and integration with sibling tools. Minor gaps like error handling are acceptable for this complexity.

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 description coverage is 100%, so parameters are already documented. The description adds context about cumulative evaluation, but does not enrich parameter semantics beyond the schema. Baseline score of 3 applies.

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?

The description clearly states the action ('submit a scoring round'), the resource ('existing fleet session'), and distinguishes from sibling tools like fleet_session_create or fleet_evaluate by specifying that it submits a round to an existing session.

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

Usage Guidelines2/5

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

The description does not provide explicit guidance on when to use this tool versus alternatives. It only mentions downstream usage (episodes can be passed to visualize, alert_check, etc.), but lacks conditions or exclusions for selecting this tool.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/collapseindex/ci-1t-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server