Skip to main content
Glama

Guard Verify

codapult_guard_verify

Run configured project, architecture, and policy checks after implementation to verify code changes without editing source. Returns structured gate results for retry decisions.

Instructions

Run the configured completion gate: selected project checks plus Guard architecture and policy checks, returning structured results. Use after implementation and semantic review; this executes project commands but does not edit source. Defaults come from agent.json where omitted. Pass requirement to bind verification to the task and increment iteration on each retry.

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_verify"
  }
}

Input Schema

NameRequiredDescriptionDefault
rootNoProject path or workspace root.
toolsNoWhether configured external verification tools are enabled; omitted uses agent.json.
checksNoProject checks to run; when omitted, uses the configured gate (normally lint, typecheck, test, and build).
strictNoEnable strict verification behavior, including failure for required but unconfigured checks.
iterationNoCurrent verification attempt, used to report whether another retry is allowed.
policy_baseNoGit ref from which to load the Guard policy for this verification.
requirementNoThe user task or acceptance requirement to include in the verification report.
changed_onlyNoLimit architecture regression checks to changed files; omitted uses configured behavior.
project_checksNoOverride whether project commands run for this invocation.
fail_on_policy_changeNoFail if the checked-out Guard policy differs from policy_base.
fail_on_protected_changesNoFail if verification-sensitive files or inline suppressions changed.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed10 schema fields changedv0.13.2
    • addedInput schema / properties / changed_only / description
      Added value: +"Limit architecture regression checks to changed files; omitted uses configured behavior."
    • changedInput schema / properties / checks / description
      Previous value: -"Checks to run; defaults to lint, typecheck, test, and build."New value: +"Project checks to run; when omitted, uses the configured gate (normally lint, typecheck, test, and build)."
    • changedInput schema / properties / fail_on_policy_change / description
      Previous value: -"Fail when the checked-out policy differs from policy_base."New value: +"Fail if the checked-out Guard policy differs from policy_base."
    • changedInput schema / properties / fail_on_protected_changes / description
      Previous value: -"Fail when verification-sensitive files or inline suppressions change."New value: +"Fail if verification-sensitive files or inline suppressions changed."
    • addedInput schema / properties / iteration / description
      Added value: +"Current verification attempt, used to report whether another retry is allowed."
    • changedInput schema / properties / policy_base / description
      Previous value: -"Git ref whose Guard policy should be used for this verification."New value: +"Git ref from which to load the Guard policy for this verification."
    • changedInput schema / properties / project_checks / description
      Previous value: -"Override completionGate.projectChecks for this invocation."New value: +"Override whether project commands run for this invocation."
    • addedInput schema / properties / requirement / description
      Added value: +"The user task or acceptance requirement to include in the verification report."
    • addedInput schema / properties / strict / description
      Added value: +"Enable strict verification behavior, including failure for required but unconfigured checks."
    • changedInput schema / properties / tools / description
      Previous value: -"External tools mode; defaults to agent.json."New value: +"Whether configured external verification tools are enabled; omitted uses agent.json."
  2. Changed1 schema field changedv0.13.0
    • addedInput schema / properties / fail_on_protected_changes
      Added value: +{
      +  "description": "Fail when verification-sensitive files or inline suppressions change.",
      +  "type": "boolean"
      +}
  3. First observed

TDQS

A4/5.0
Behavior4/5

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

With no annotations provided, the description carries the full burden and does well: it discloses that this executes project commands, that it does not edit source, that it can fail on policy drift or protected changes via params, and that iteration controls retry reporting. It omits operational traits such as runtime cost of a full lint/typecheck/test/build sweep and whether build artifacts are written.

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?

Three front-loaded sentences with no filler; purpose comes first, then timing, then the defaults/retry contract. Slightly dense, but every clause carries information an agent needs.

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 an 11-param, no-annotation tool this covers purpose, defaults, side-effect boundary, and retry semantics well. The remaining gap is that no output schema exists, yet "returning structured results" is never expanded enough for the agent to know what the report contains or how to read pass/fail.

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 earns above that by explaining the cross-cutting default rule ("Defaults come from agent.json where omitted") which governs several boolean params, and by giving the intent behind requirement and iteration. It does not add format or behavior detail beyond the schema for individual flags.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: "Run the configured completion gate: selected project checks plus Guard architecture and policy checks, returning structured results." That is far more precise than the sibling guard_check or guard_review names alone, but it never explicitly says how it differs from codapult_guard_check, so the agent must infer the split.

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?

"Use after implementation and semantic review" gives a clear lifecycle position, and "Pass requirement to bind verification to the task and increment iteration on each retry" prescribes call-site behavior. It stops short of naming alternatives or exclusions (e.g. when to prefer guard_check alone).

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