axint

axint.xcode.guard

Checks project memory and Axint session integrity to prevent context loss during long Xcode tasks. Writes a guard proof and optionally starts a session to maintain state consistency.

Instructions

Guard an Xcode agent session against context compaction and Axint drift. Checks project memory files, active Axint session, latest Axint Run or guard proof, and long-task freshness. Writes... Use: call around long Xcode tasks, context recovery, broad Swift edits, or before claiming runtime proof. Effects: writes .axint/guard proof and may start a session; does not edit app source or use network.

Input Schema

TableJSON Schema

Name	Required	Description
`cwd`	No	Project directory to guard. Defaults to the MCP process cwd.
`projectName`	No	Project name for the guard report.
`expectedVersion`	No	Expected Axint version for the active project.
`platform`	No	Target Apple platform, such as macOS, iOS, visionOS, or all.
`stage`	No	Current Xcode workflow stage. Defaults to context-recovery.
`sessionToken`	No	Current axint.session.start token, if already known.
`modifiedFiles`	No	Files in scope for this task.
`notes`	No	Agent/user notes to scan for compaction, drift, forgotten Axint usage, or long-task risk.
`lastAxintTool`	No	Last Axint tool the agent used, e.g. axint.suggest or axint.feature.
`lastAxintResult`	No	Short result from the last Axint tool call.
`maxMinutesSinceAxint`	No	Maximum allowed minutes since latest Axint evidence. Defaults to 10.
`autoStartSession`	No	Whether to start axint.session.start automatically if no active session exists. Defaults to true.
`writeReport`	No	Whether to write .axint/guard/latest.json and latest.md. Defaults to true.
`format`	No	Output format. Defaults to markdown.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`text`	Yes	Primary Axint tool response text, matching the first text content block.
`isError`	No	Whether Axint marked the tool response as an error.

Tool Definition Quality

A4.5/5.0

Behavior5/5

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

The description fully discloses behavioral traits: checks files, writes proof, may start session, and explicitly states 'does not edit app source or use network.' This adds value beyond annotations, which only state readOnlyHint and destructiveHint are false.

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 (5 sentences), front-loaded with purpose, then operations, usage, and effects. Every sentence adds value with no redundancy.

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 the high parameter count and presence of an output schema, the description provides sufficient context: what the tool checks, what it writes, when to use it, and its side effects. It is complete for an AI agent to understand and invoke correctly.

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 coverage is 100% with all 14 parameters described. The description does not add much beyond the schema but provides context for the tool's overall behavior. Baseline 3 is appropriate.

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: 'Guard an Xcode agent session against context compaction and Axint drift.' It specifies actions (checks, writes proof, may start session) and distinguishes it from sibling tools like axint.session.start and axint.run by focusing on guarding and state preservation.

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 explicitly lists when to use the tool: 'around long Xcode tasks, context recovery, broad Swift edits, or before claiming runtime proof.' It does not provide exclusions or alternatives, but the scenarios given are sufficient for an AI agent to decide.

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

Install Server

Latest Blog Posts

Lightport: Open-Sourcing Glama's AI Gateway
By punkpeye on April 27, 2026.
open source
OpenAI
Tool Definition Quality Score (TDQS)
By punkpeye on April 3, 2026.
mcp
The Hackers Who Tracked My Sleep Cycle
By punkpeye on March 26, 2026.
security

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/agenticempire/axint'

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