Skip to main content
Glama

Prepare Guard Review

codapult_guard_review

Build a bounded packet with diff, project context, contracts, and deterministic guard findings for human or AI semantic review after coding; it informs review, not approval or verification.

Instructions

Build a bounded packet for an AI semantic reviewer containing the diff, project context, active contracts, and deterministic Guard findings. Use after coding and before verification. The result needs human/agent review; it is not itself an approval or verification. Set base for PR comparisons and requirement to focus the review.

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_review"
  }
}

Input Schema

NameRequiredDescriptionDefault
baseNoGit base ref for PR review, e.g. origin/main.
rootNoProject path or workspace root.
requirementNoThe task requirement the reviewer should assess.
changed_onlyNoInclude only changed-file findings and baseline-aware results; false requests a full-scope packet.
max_diff_charsNoMaximum number of diff characters included in the packet.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv0.13.2
    • addedInput schema / properties / changed_only / description
      Added value: +"Include only changed-file findings and baseline-aware results; false requests a full-scope packet."
    • addedInput schema / properties / max_diff_chars / description
      Added value: +"Maximum number of diff characters included in the packet."
    • addedInput schema / properties / requirement / description
      Added value: +"The task requirement the reviewer should assess."
  2. First observed

TDQS

A3.8/5.0
Behavior3/5

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

With no annotations, the description carries the full burden; it does disclose that output is a bounded packet requiring downstream human/agent review and that it does not itself approve or verify — valuable framing. However, it never states whether the call mutates the workspace (writes a packet file?), what permissions or prerequisites it needs, or how large a default packet becomes.

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?

Four short sentences, front-loaded with the core action and artifact before the usage note and caveat. Every sentence contributes; minor redundancy between 'bounded packet' and the max_diff_chars parameter is not harmful.

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?

With no output schema and no annotations, the description steps up by naming the packet's four contents and stressing that the result is input to review rather than a verdict. The remaining gap is the concrete return shape/serialization of the packet, but an agent has enough to call this correctly.

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 the baseline is 3, but the description adds genuine semantic value by explaining that 'base' exists for PR comparisons and 'requirement' focuses the review — intent the schema text alone only partially conveys. It says nothing extra about changed_only or max_diff_chars, keeping it at a solid 4 rather than a 5.

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 artifact: 'Build a bounded packet for an AI semantic reviewer,' then enumerates its contents (diff, project context, active contracts, Guard findings). It implicitly separates itself from codapult_guard_verify by noting it is 'not itself an approval or verification,' though it never names a sibling directly.

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 coding and before verification' gives a clear lifecycle position, and the sentence 'it is not itself an approval or verification' draws the boundary against the verify/check siblings. It stops short of naming an explicit alternative for when this tool is the wrong choice.

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