Skip to main content
Glama

axint.workflow.check

Read-onlyIdempotent

Validates workflow stage gates by checking required Axint session actions, ensuring compliance before planning, writing, or building.

Instructions

Read-only agent workflow gate. Requires the current Axint session token from axint.session.start unless requireSession=false is explicitly set. Use this at session start, after context compaction, before planning, writing, building, or... Use: use at stage gates to prove Axint workflow coverage; not a final build/test substitute. Effects: read-only gate but may update tiny workflow freshness stamps; no network.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
cwdNoProject directory containing .axint/session/current.json. Defaults to the MCP process cwd.
sessionStartedNoWhether axint.session.start was called in this chat/recovery pass.
agentNoAgent host/tool lane for this gate. Codex/Claude/Cowork/Cursor use patch-first lanes; Xcode may use Xcode...
sessionTokenNoToken returned by axint.session.start. Required by default so compaction cannot erase the Axint workflow...
requireSessionNoSet false only for legacy/manual checks. Defaults to true.
stageNoWorkflow stage being checked. Defaults to pre-build.
surfacesNoApple surfaces touched by this task. If omitted, inferred from modifiedFiles.
modifiedFilesNoFiles changed in this agent pass, used to infer whether Swift validation is required.
ranSuggestNoWhether axint.suggest was used during planning.
ranStatusNoWhether axint.status was called to confirm the running MCP version.
readRehydrationContextNoWhether .axint/AXINT_REHYDRATE.md was read after a new chat, context compaction, MCP restart, or drift.
readAgentInstructionsNoWhether AGENTS.md, CLAUDE.md, or .axint/project.json was read after a new chat or context compaction.
readDocsContextNoWhether .axint/AXINT_DOCS_CONTEXT.md was read or axint.context.docs was called after a new chat or context...
ranFeatureNoWhether axint.feature was used for a new surface scaffold.
ranRepairNoWhether axint.repair was used for an existing-code repair plan. This satisfies planning for patch-first...
featureBypassReasonNoConcrete reason axint.feature was intentionally bypassed. Use for existing-code edits, patch-first repairs,...
ranSwiftValidateNoWhether axint.swift.validate was run on modified Swift.
ranCloudCheckNoWhether axint.cloud.check was run with source/evidence.
xcodeBuildPassedNoWhether Xcode build evidence passed.
xcodeTestsPassedNoWhether focused unit/UI tests passed.
notesNoOptional human/agent context for why a step was skipped.
availableToolsNoOptional list of Axint MCP tools visible in this host session. When supplied, workflow.check will not...
formatNoOutput format. Defaults to markdown.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
textYesPrimary Axint tool response text, matching the first text content block.
isErrorNoWhether Axint marked the tool response as an error.
Behavior4/5

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

Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds that it 'may update tiny workflow freshness stamps' and 'no network', providing useful behavioral context beyond the structured fields.

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 a single paragraph that front-loads key information (purpose, prerequisite, usage). It is concise with no filler, though slightly denser than ideal.

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?

Given the complexity (23 parameters) and presence of output schema and annotations, the description covers core usage, prerequisites, and effects. It omits error handling but is sufficient for a well-documented tool.

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 detailed parameter descriptions. The tool's main description repeats some parameter information (e.g., session token requirement) but does not add significant new semantic detail beyond the schema.

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 it is a 'Read-only agent workflow gate' used at specific stages (session start, after context compaction, before planning, etc.), and explicitly distinguishes it from final build/test substitutes, making its purpose unambiguous.

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?

The description provides explicit guidance on when to use it ('at stage gates to prove Axint workflow coverage'), prerequisites (session token unless requireSession=false), and what it is not for ('not a final build/test substitute').

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

Install Server

Other Tools

Latest Blog Posts

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