Skip to main content
Glama

Refresh Guard Model

codapult_guard_analyze

Refresh repository discovery and persist current project facts and snapshots after changes, returning the new revision and discovery metrics without altering Guard rules, contracts, or baseline.

Instructions

Rediscover the repository and persist its current project facts and snapshots. Use after repository changes when codapult_guard_next_action returns needs-refresh or needs-setup; this does not change Guard rules, contracts, or baseline. Returns the new revision and discovery metrics.

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": "codapult_guard_analyze"
  }
}

Input Schema

NameRequiredDescriptionDefault
rootNoProject path or workspace root.
confirmNoRequired before writing refreshed Guard state.
no_waitNoReturn immediately if another process holds the Guard state lock.
wait_msNoMaximum time to wait for the Guard state lock, in milliseconds.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.13.2
    • addedInput schema / properties / no_wait / description
      Added value: +"Return immediately if another process holds the Guard state lock."
    • addedInput schema / properties / wait_ms / description
      Added value: +"Maximum time to wait for the Guard state lock, in milliseconds."
  2. First observed

TDQS

A4.4/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does disclose that this is a state-persisting (write) operation, what it leaves untouched (rules, contracts, baseline), and what it returns (new revision, discovery metrics). It stops short of covering lock contention behavior, idempotency, or that a confirmation flag is required before any write actually lands.

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?

Three short sentences, front-loaded with the action, then the trigger, then the scope exclusion and return value. Nothing is redundant and no sentence merely restates the tool name.

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 no-annotation write tool it covers action, trigger, scope boundaries, and return payload compactly, which is enough to call it correctly. The gap is that the confirm-gated write path and lock contention semantics live only in the schema, so an agent skimming the description could attempt a refresh without realizing a confirmation is needed.

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%, so root, confirm, no_wait, and wait_ms are already documented in structured data. The description adds no parameter-level detail such as when to set no_wait versus raising wait_ms, so it sits at the baseline for a fully documented 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 first sentence gives a specific verb pair and resource: rediscover the repository and persist its project facts and snapshots. The description also implicitly separates it from siblings like guard_propose or guard_init by framing this as a refresh of existing discovered state rather than authoring rules.

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 states the exact triggering condition (after repository changes, when codapult_guard_next_action returns needs-refresh or needs-setup) and names the sibling that produces that signal. It also carves out scope explicitly: this does not change Guard rules, contracts, or baseline, which routes the agent away from tools like propose or init.

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