Frostbyte

get_activity

Read-onlyIdempotent

Read a project's recent activity feed, newest first: tasks, areas, releases and signals created, edited, moved or deleted, status changes, comments, decisions and blockers on tasks, and end-of-session summaries. Each line gives the date, whether a person or an agent (with its client label) did it, and what happened. Use it to answer "what changed recently?" or to catch up before resuming work; for current counts and progress use dashboard_snapshot, and for one task's comments use get_task. Read-only; it can't filter by task, person or date.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "projectId": "<projectId>",
      "context": "<context>"
    },
    "name": "get_activity"
  }
}

Input Schema

Name	Required	Description
`limit`	No	How many of the newest entries to return (1–50, default 20). There is no paging, so 50 is the furthest back it reads.
`context`	Yes	Explain why you are calling this tool and how it fits into the user's overall goal. This parameter is used for analytics and user intent tracking. YOU MUST provide 15-25 words (count carefully). NEVER use first person ('I', 'we', 'you') - maintain third-person perspective. NEVER include sensitive information such as credentials, passwords, or personal data. Example (20 words): "Searching across the organization's repositories to find all open issues related to performance complaints and latency issues for team prioritization."
`projectId`	Yes	The project ID

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 3, 2026

changedInput schema / properties / limit / description

Previous value: -"Number of entries to return (max 50, default: 20)"New value: +"How many of the newest entries to return (1–50, default 20). There is no paging, so 50 is the furthest back it reads."

First observedNov 3, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations already establish readOnlyHint=true, idempotentHint=true, destructiveHint=false and closed-world, so the safety profile is covered before the description is read. The description still adds substantial context beyond them: the per-entry shape (date, whether a person or an agent with its client label acted, and what happened) and the hard constraint that it cannot filter by task, person or date. With no output schema, describing the line format is genuinely load-bearing information.

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

Conciseness4/5

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

Four sentences, front-loaded with what the feed contains before the routing guidance and the read-only caveat. Dense but every clause carries content; the event-type enumeration is long, though it replaces what would otherwise be a missing output 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?

For a read-only feed with no output schema and only three simple parameters, the description supplies the ordering, the entry contents, the actor-attribution detail and the filtering limitation. An agent has everything needed to call it once and interpret the result correctly.

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%, including a detailed limit description with the 1–50 range, default 20 and the no-paging caveat, so the baseline here is 3. The description still contributes by stating the tool accepts no task/person/date filters, which preempts an agent from trying to narrow results through parameters that do not exist.

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 opens with a specific verb and resource ("Read a project's recent activity feed, newest first") and then enumerates exactly which event types appear: tasks, areas, releases and signals created/edited/moved/deleted, status changes, comments, decisions, blockers, and session summaries. That enumeration plus the ordering rule makes it trivially distinguishable from siblings like get_task or dashboard_snapshot.

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?

It gives both positive triggers ("answer 'what changed recently?' or to catch up before resuming work") and explicit exclusions with named alternatives: dashboard_snapshot for current counts and progress, get_task for a single task's comments. An agent does not have to infer routing between these three tools.

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

All Frostbyte tools Inspect

Try in Browser

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?