Skip to main content
Glama

board_log_activity

Log arbitrary observations, decisions, or blockers to the write-only audit stream. Use for free-form comments or context that must persist across agent sessions.

Instructions

Append an entry to the activity_log — a write-only audit stream of what agents did, decided, or observed. Use this for: RESEARCH observations the next session should see, decisions made during PLAN/REVIEW, blockers, notable failures, or any context that shouldn't be lost. Most status/assignment changes via board_update_task and board_create_task already write their own activity_log entries automatically — call this explicitly for free-form comments (action='commented') or arbitrary actions. Read back via board_get_activity. Returns { id, action, message }.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
agent_nameYesName of the agent (free-form string — e.g., 'main', 'code-reviewer', 'gcp-infra'). Used for filtering and audit.
actionYesAction type. Fixed enum. Most values correspond to lifecycle events written automatically by other tools; use 'commented' for free-form notes/observations logged manually.
detailsNoHuman-readable description of what happened. Required in practice for 'commented' — without it, the entry is empty.
task_idNoRelated task ID if this activity is about a specific task. Enables filtering via board_get_activity(task_id=...). Omit for project-level or session-level events.
session_idNoRelated session ID if this activity is scoped to a specific session. Enables filtering via board_get_activity(session_id=...).
metadataNoOptional structured payload (e.g., { commit_sha: 'abc123', build_id: 'build-456' }). Stored verbatim, not indexed.

Implementation Reference

  • The handler function for board_log_activity. Writes an entry to the 'activity_log' Firestore collection with agent_name, action, details, task_id, session_id, metadata, and a created_at timestamp. Returns the document id, action, and a success message.
    async ({ agent_name, action, details, task_id, session_id, metadata }) => {
      const docRef = await db.collection("activity_log").add({
        task_id: task_id ?? null,
        session_id: session_id ?? null,
        agent_name,
        action,
        details: details ?? null,
        metadata: metadata ?? {},
        created_at: Timestamp.now(),
      });
    
      return {
        content: [
          {
            type: "text" as const,
            text: JSON.stringify(
              {
                id: docRef.id,
                action,
                message: "Activity logged successfully",
              },
              null,
              2
            ),
          },
        ],
      };
    }
  • Zod schema defining the input parameters for board_log_activity: agent_name (string, required), action (enum of 9 values, required), details (optional string), task_id (optional string), session_id (optional string), metadata (optional record).
    {
      agent_name: z.string().describe("Name of the agent (free-form string — e.g., 'main', 'code-reviewer', 'gcp-infra'). Used for filtering and audit."),
      action: z
        .enum([
          "created",
          "updated",
          "claimed",
          "blocked",
          "completed",
          "commented",
          "mode_changed",
          "session_started",
          "session_ended",
        ])
        .describe("Action type. Fixed enum. Most values correspond to lifecycle events written automatically by other tools; use 'commented' for free-form notes/observations logged manually."),
      details: z.string().optional().describe("Human-readable description of what happened. Required in practice for 'commented' — without it, the entry is empty."),
      task_id: z.string().optional().describe("Related task ID if this activity is about a specific task. Enables filtering via board_get_activity(task_id=...). Omit for project-level or session-level events."),
      session_id: z.string().optional().describe("Related session ID if this activity is scoped to a specific session. Enables filtering via board_get_activity(session_id=...)."),
      metadata: z
        .record(z.string(), z.unknown())
        .optional()
        .describe("Optional structured payload (e.g., { commit_sha: 'abc123', build_id: 'build-456' }). Stored verbatim, not indexed."),
    },
  • Registration of board_log_activity via server.tool() in the registerActivityTools function. Called from src/index.ts line 31.
    server.tool(
      "board_log_activity",
      "Append an entry to the activity_log — a write-only audit stream of what agents did, decided, or observed. Use this for: RESEARCH observations the next session should see, decisions made during PLAN/REVIEW, blockers, notable failures, or any context that shouldn't be lost. Most status/assignment changes via board_update_task and board_create_task already write their own activity_log entries automatically — call this explicitly for free-form comments (action='commented') or arbitrary actions. Read back via board_get_activity. Returns { id, action, message }.",
      {
        agent_name: z.string().describe("Name of the agent (free-form string — e.g., 'main', 'code-reviewer', 'gcp-infra'). Used for filtering and audit."),
        action: z
          .enum([
            "created",
            "updated",
            "claimed",
            "blocked",
            "completed",
            "commented",
            "mode_changed",
            "session_started",
            "session_ended",
          ])
          .describe("Action type. Fixed enum. Most values correspond to lifecycle events written automatically by other tools; use 'commented' for free-form notes/observations logged manually."),
        details: z.string().optional().describe("Human-readable description of what happened. Required in practice for 'commented' — without it, the entry is empty."),
        task_id: z.string().optional().describe("Related task ID if this activity is about a specific task. Enables filtering via board_get_activity(task_id=...). Omit for project-level or session-level events."),
        session_id: z.string().optional().describe("Related session ID if this activity is scoped to a specific session. Enables filtering via board_get_activity(session_id=...)."),
        metadata: z
          .record(z.string(), z.unknown())
          .optional()
          .describe("Optional structured payload (e.g., { commit_sha: 'abc123', build_id: 'build-456' }). Stored verbatim, not indexed."),
      },
      async ({ agent_name, action, details, task_id, session_id, metadata }) => {
        const docRef = await db.collection("activity_log").add({
          task_id: task_id ?? null,
          session_id: session_id ?? null,
          agent_name,
          action,
          details: details ?? null,
          metadata: metadata ?? {},
          created_at: Timestamp.now(),
        });
    
        return {
          content: [
            {
              type: "text" as const,
              text: JSON.stringify(
                {
                  id: docRef.id,
                  action,
                  message: "Activity logged successfully",
                },
                null,
                2
              ),
            },
          ],
        };
      }
    );
  • The ActivityLog interface in src/types.ts defines the data shape stored in Firestore, matching the tool's schema and handler output.
    export interface ActivityLog {
      task_id: string | null;
      session_id: string | null;
      agent_name: string;
      action:
        | "created"
        | "updated"
        | "claimed"
        | "blocked"
        | "completed"
        | "commented"
        | "mode_changed"
        | "session_started"
        | "session_ended";
      details: string | null;
      metadata: Record<string, unknown>;
      created_at: Timestamp;
    }
Behavior4/5

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

No annotations provided, so the description carries the burden. It declares write-only behavior, return structure ({ id, action, message }), and that action is an enum. Does not discuss idempotency or side effects, but adequately conveys core behavior.

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 paragraphs are concise and well-organized. The first sentence front-loads the purpose. Every sentence adds value, avoiding redundancy with the schema.

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?

Given no annotations and no output schema, the description thoroughly covers purpose, usage, parameter semantics, return value, and ties to sibling tools. Leaves no significant gaps for an agent to misunderstand.

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

Parameters5/5

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

Schema coverage is 100%, and the description adds significant context beyond the schema: explains use of 'commented' action, details requirement for 'commented', purpose of task_id/session_id for filtering, and that metadata is stored verbatim and unindexed.

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 tool's purpose: appending entries to an activity_log as a write-only audit stream. It distinguishes itself from sibling tools that auto-log lifecycle events, emphasizing use for free-form comments and arbitrary actions.

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?

Explicitly describes when to use (research observations, decisions, blockers, failures) and when not to (status/assignment changes are auto-logged). Provides alternatives like board_get_activity for reading and notes that board_update_task/board_create_task auto-log.

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/HuntsDesk/ve-vibe-board'

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