Skip to main content
Glama
Sign In
Kiln

Kiln

by codeofaxel
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python

pull_reflog_from_cloud

Read-only

Read cloud reflog entries to see what teammates changed from their machines. Filter by branch or artifact type; requires Kiln Pro.

Instructions

Read entries from the cloud reflog — shows what teammates did from their machines.

Needs Kiln Pro.

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": "pull_reflog_from_cloud"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoThe most entries to return. Default: 100.
branch_idNoOnly entries for this branch. Omitted, every branch.
artifact_typeNoOnly entries for this kind of branch: ``design``, ``preset`` or ``feature``. Omitted, every kind.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv1.5.1
    • addedInput schema / properties / artifact_type / description
      Added value: +"Only entries for this kind of branch: ``design``, ``preset`` or ``feature``.  Omitted, every kind."
    • addedInput schema / properties / branch_id / description
      Added value: +"Only entries for this branch.  Omitted, every branch."
    • changedInput schema / properties / limit / description
      Previous value: -"Default: 100."New value: +"The most entries to return. Default: 100."
  2. Addedv1.5.0

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds two things the annotations do not: a tier prerequisite ("Needs Kiln Pro") and the fact that entries reflect what teammates did remotely, which explains why this differs from a local reflog read. Ordering or pagination behavior remains undisclosed.

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 short lines with zero filler: the purpose and interpretation of the data come first, the prerequisite second. Every sentence carries information the agent cannot get from the name or schema.

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 read-only, zero-required-parameter tool with full schema coverage and annotations, the definition supplies the outstanding piece — the Kiln Pro tier gate that would otherwise cause a mysterious failure. No output schema exists, so a note on what a returned entry contains would still add slight value.

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%, and each of the three optional parameters (limit, branch_id, artifact_type) already has prose explaining its filter semantics and omission behavior. The description adds nothing about parameter format or interaction, so the baseline 3 applies.

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 description uses a specific verb and resource ("Read entries from the cloud reflog") and clarifies what the data represents — teammate actions from their own machines. It does not explicitly distinguish itself from the local sibling show_reflog or from get_reflog_entry, so an agent must infer the cloud-vs-local split from the name.

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

Usage Guidelines3/5

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

The word "cloud" plus the teammate framing implies when to reach for this over show_reflog, but the guidance is implicit only. There is no explicit "use this instead of X when..." statement, and no note that results are filtered by the optional limit/branch/artifact_type parameters.

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

Deploy Server

Other Tools