Skip to main content
Glama

Axint

by io.github.agenticempire

axint.xcode.write

Write a file inside the Xcode project through the Axint guard path. For Swift files, runs axint.swift.validate and axint.cloud.check immediately, then records .axint/guard/latest.* proof. Use this instead of raw XcodeWrite when an agent is editing Apple-native files during a long task. Use: use only for guarded Xcode-project file writes; outside Xcode, patch normally and validate after. Inputs: path must remain inside cwd; createDirs, validateSwift, and cloudCheck default true. Effects: writes the requested file inside cwd, may create dirs, validates Swift, and may write guard/check artifacts.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
cwdNoProject root. Defaults to the MCP process cwd.
pathYesFile path to write. Relative paths are resolved inside cwd; absolute paths must still be inside cwd.
notesNoAgent notes or user feedback to scan for drift while writing.
formatNoOutput format. Defaults to markdown.
contentYesFull file contents to write.
platformNoTarget Apple platform for Cloud Check.
cloudCheckNoWhether to run Cloud Check for .swift files. Defaults to true.
createDirsNoWhether to create parent directories before writing. Defaults to true.
projectNameNoProject name for guard/session reports.
sessionTokenNoCurrent axint.session.start token, if already known.
validateSwiftNoWhether to run Swift validation for .swift files. Defaults to true.
expectedVersionNoExpected Axint version for this project.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
textYes
isErrorNo

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed2 schema fields changed
    • removedOutput schema / properties / isError / description
      Removed value: -"Whether Axint marked the tool response as an error."
    • removedOutput schema / properties / text / description
      Removed value: -"Primary Axint tool response text, matching the first text content block."
  2. Changed6 schema fields changed
    • changedInput schema / properties / cloudCheck / description
      Previous value: -"Whether to run Cloud Check for .swift files...."New value: +"Whether to run Cloud Check for .swift files. Defaults to true."
    • changedInput schema / properties / createDirs / description
      Previous value: -"Whether to create parent directories before..."New value: +"Whether to create parent directories before writing. Defaults to true."
    • changedInput schema / properties / notes / description
      Previous value: -"Agent notes or user feedback to scan for..."New value: +"Agent notes or user feedback to scan for drift while writing."
    • changedInput schema / properties / path / description
      Previous value: -"File path to write. Relative paths are..."New value: +"File path to write. Relative paths are resolved inside cwd; absolute paths must still be inside cwd."
    • changedInput schema / properties / sessionToken / description
      Previous value: -"Current axint.session.start token, if..."New value: +"Current axint.session.start token, if already known."
    • changedInput schema / properties / validateSwift / description
      Previous value: -"Whether to run Swift validation for .swift..."New value: +"Whether to run Swift validation for .swift files. Defaults to true."
  3. Changed13 schema fields changed
    • addedInput schema / properties / cloudCheck / description
      Added value: +"Whether to run Cloud Check for .swift files...."
    • addedInput schema / properties / content / description
      Added value: +"Full file contents to write."
    • addedInput schema / properties / createDirs / description
      Added value: +"Whether to create parent directories before..."
    • addedInput schema / properties / cwd / description
      Added value: +"Project root. Defaults to the MCP process cwd."
    • addedInput schema / properties / expectedVersion / description
      Added value: +"Expected Axint version for this project."
    • addedInput schema / properties / format / description
      Added value: +"Output format. Defaults to markdown."
    • addedInput schema / properties / notes / description
      Added value: +"Agent notes or user feedback to scan for..."
    • addedInput schema / properties / path / description
      Added value: +"File path to write. Relative paths are..."
    • addedInput schema / properties / platform / description
      Added value: +"Target Apple platform for Cloud Check."
    • addedInput schema / properties / projectName / description
      Added value: +"Project name for guard/session reports."
    • addedInput schema / properties / sessionToken / description
      Added value: +"Current axint.session.start token, if..."
    • addedInput schema / properties / validateSwift / description
      Added value: +"Whether to run Swift validation for .swift..."
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "additionalProperties": false,
+  "properties": {
+    "isError": {
+      "description": "Whether Axint marked the tool response as an error.",
+      "type": "boolean"
+    },
+    "text": {
+      "description": "Primary Axint tool response text, matching the first text content block.",
+      "type": "string"
+    }
+  },
+  "required": [
+    "text"
+  ],
+  "type": "object"
+}
  4. Added

TDQS

A4.5/5.0
Behavior4/5

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

Annotations are all false and provide no safety hints, so the description carries the burden and mostly delivers: it reveals that Swift files trigger immediate validation and cloud check, writes .axint/guard/latest.* proof, may create directories, and may write guard/check artifacts. However, it does not disclose failure behavior (e.g., what happens if validation fails) or permission requirements, so it is not fully transparent, but still strong.

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 front-loaded with the core purpose and uses short sentences, but it repeats the 'use' guidance twice ('Use this instead of raw XcodeWrite...' and 'Use: use only for guarded...') and includes a somewhat redundant 'Effects' section that restates earlier points. Still, it remains reasonably tight and easy to scan.

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 tool with 12 parameters, two Swift validation steps, and artifact writing, the description covers purpose, usage context, effects, and default parameter values. It does not describe return values, but an output schema exists so that is acceptable. Missing details like failure handling or integration with session tokens are minor gaps.

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 description coverage is 100%, so the baseline is 3, but the description adds extra meaning by pointing out defaults ('createDirs, validateSwift, and cloudCheck default true') and the constraint that 'path must remain inside cwd.' It also links behavior to parameters (Swift validation/cloud check) beyond schema text, adding genuine value.

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 ('Write a file inside the Xcode project through the Axint guard path') and explains the unique guard/validation behavior. It further distinguishes itself from 'raw XcodeWrite' and states it is for Apple-native files during long tasks, which clearly separates it from sibling tools like axint.xcode.guard or axint.swift.validate.

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 explicitly instructs 'Use this instead of raw XcodeWrite when an agent is editing Apple-native files during a long task' and then provides a clear exclusion: 'outside Xcode, patch normally and validate after.' This gives both positive and negative usage guidance, fully differentiating it from alternatives.

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