Skip to main content
Glama

Axint

by io.github.agenticempire

axint.xcode.guard

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. Use: call around long Xcode tasks, context recovery, broad Swift edits, or before claiming runtime proof; use workflow.check. Inputs: stage selects the gate; modifiedFiles and notes narrow drift checks; autoStartSession defaults true. Effects: writes .axint/guard proof and may start a session; does not edit app source or use network.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
cwdNoProject directory to guard. Defaults to the MCP process cwd.
notesNoAgent/user notes to scan for compaction, drift, forgotten Axint usage, or.
stageNoCurrent Xcode workflow stage. Defaults to context-recovery.
formatNoOutput format. Defaults to markdown.
platformNoTarget Apple platform, such as macOS, iOS, visionOS, or all.
projectNameNoProject name for the guard report.
writeReportNoWhether to write .axint/guard/latest.json and latest.md. Defaults to true.
sessionTokenNoCurrent axint.session.start token, if already known.
lastAxintToolNoLast Axint tool the agent used, e.g. axint.suggest or axint.feature.
modifiedFilesNoFiles in scope for this task.
expectedVersionNoExpected Axint version for the active project.
lastAxintResultNoShort result from the last Axint tool call.
autoStartSessionNoWhether to start axint.session.start automatically if no active session exists.
maxMinutesSinceAxintNoMaximum allowed minutes since latest Axint evidence. Defaults to 10.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
textYes
isErrorNo

TDQS

A4.8/5.0
Behavior5/5

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

Annotations are all false, so the description carries full burden. It explicitly discloses effects: 'writes .axint/guard proof and may start a session' and non-effects: 'does not edit app source or use network.' This goes beyond what annotations provide and gives essential behavioral context.

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?

The description is well-structured with clear sections (purpose, checks, usage, inputs, effects). It is moderately long but every sentence provides useful information, earning a score above the mid-range, though not a perfect 5 due to some logical density.

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 tool's complexity (14 params, many siblings), the description is highly complete: it conveys purpose, when to use, side effects, key parameter semantics, and alternatives. It doesn't need to explain return values because an output schema exists. This is a comprehensive, production-ready description.

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%, so baseline is 3. The description adds meaning beyond the schema by explaining the roles of key parameters: 'stage selects the gate; modifiedFiles and notes narrow drift checks; autoStartSession defaults true.' This highlights semantics not obvious from the bare schema, justifying a 4.

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 further specifies the checks performed (project memory, active session, latest Run/proof, freshness). It also distinguishes from a sibling by mentioning 'use workflow.check' as an alternative.

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?

Explicit usage guidance is provided: 'call around long Xcode tasks, context recovery, broad Swift edits, or before claiming runtime proof.' It also names an alternative tool ('use workflow.check') and clarifies when to consider it, giving clear context for selection.

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

All Axint toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.1/5.0
Disambiguation4/5

Most tools have clearly distinct purposes, with descriptions specifying exact use cases (e.g., axint.activate for smoke test, axint.status for version). There is minor potential overlap between axint.suggest and axint.feature, but descriptions clarify suggestion vs generation.

Naming Consistency5/5

All tools follow a consistent hierarchical pattern: 'axint.<category>.<action>' (e.g., axint.agent.advice, axint.swift.validate). Even standalone tools like axint.compile fit the pattern. No mixing of conventions.

Tool Count2/5

36 tools is well above the typical 3-15 range for a well-scoped set. While the server covers a broad domain, the sheer number may overwhelm agents and reduce efficiency. A reduction or grouping would improve coherence.

Completeness4/5

The tool set covers the full Axint development lifecycle: installation, compilation, validation, repair, upgrade, session management, and coordination. Minor gaps exist (e.g., no dedicated tool for deleting project artifacts), but core workflows are well-supported.

Resources