Skip to main content
Glama

Read the setup journal

get_setup_journal
Read-onlyIdempotent

Read this Project's setup journal and human-action links. Administrator-only. Without wait_for_step, since returns unchanged when nothing moved. since is ignored when wait_for_step is set; a wait always returns the full entry list, subject to filtering and limit. include_complete and include_superseded default to false; failed entries remain visible. limit defaults to 200 and sets truncated when applied; raise it to read more. Hidden entries are omitted unless explicitly watched. A watched entry always remains in the result, even when hidden. wait_for_step returns when that entry changes state or timeout_seconds expires (default 25; negative refused; 0 reads once without waiting; positive budgets clamped to 1..25), including its current state and timed_out. If timed_out is true, call again with the same wait_for_step instead of increasing timeout_seconds. Completions without a journal write are observed on a few-second cadence (every five unchanged ticks and once before expiry). The first read precedes the wait budget; transient polling failures retry until timeout and return last_error with the last known state. Observes components without seeding connectors.

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": "get_setup_journal"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoPositive integer entry limit, default 200; truncated indicates omitted entries. Raise it to read more.
sinceNoVersion returned by an earlier journal read; ignored when wait_for_step is set (still validated). A wait always returns the full entry list, subject to filtering and limit
wait_for_stepNoStep UUID to wait for; hidden entries remain watchable and are included in the result; already-terminal steps return immediately; with application_id, that Application's steps from earlier rounds are watchable too, but a step outside its view belonging to the Project or another Application, even one a call for this build returned, only without it
application_idNoOptional Application UUID. Selects its current build: its goal, builder and app steps, the Project's agent connection and builder invitations, and the shared steps opened for it in this round; cursors are tagged with this view. Read without application_id for every Project step.
timeout_secondsNoWait budget: negative is invalid; 0 reads once without waiting; positive values clamp to 1..25 seconds (default 25)
include_completeNoInclude completed entries, default false
include_supersededNoInclude superseded entries, default false

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior5/5

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

Beyond the annotations, it discloses administrator-only access, hidden and watched entry behavior, timeout clamping, retry behavior on transient polling failures, last_error reporting, and that completions without a journal write are observed on a cadence. These are substantial behavioral details that an agent could not infer from readOnly/idempotent hints alone.

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?

The purpose is front-loaded and most content is relevant, but the description is long and dense, with several clauses packed into single sentences. It also repeats schema descriptions rather than focusing only on behavior that the schema does not already explain.

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?

For a complex read tool with no output schema, it covers the important operational behavior: waiting, timeout, truncation, hidden entries, retries, and error reporting. It does not describe the structure of journal entries or the full response shape, but it provides enough to call the tool 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 already 100%, but the description still adds cross-parameter meaning: since is ignored when waiting, waits return the full filtered list, hidden entries are omitted unless watched, and timeout values have specific semantics. Much of this overlaps the schema text, so it is not fully additive.

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 states a specific verb and resource: read this Project's setup journal and human-action links. It is clearly a read tool, but it does not explicitly name or contrast sibling tools such as get_pending_action or record_setup_step.

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?

The description gives clear operational guidance for the two main modes: without wait_for_step it reads and can use since efficiently, while wait_for_step blocks for a state change. It also says to retry with the same wait_for_step after timed_out, though it does not compare this tool against alternative sibling tools.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources