Skip to main content
Glama

Guard Proposals

codapult_guard_propose

Generate evidence-backed candidate architecture rules and contracts from the current project model to review policy after setup or structural changes; proposals are never activated automatically.

Instructions

Generate evidence-backed candidate architecture rules and contracts from the current project model. Use to review possible policy after setup or structural changes; proposals are never activated automatically. The result includes evidence, questions, freshness, and persistence status. Persisted proposals still require an explicit decision with codapult_guard_proposal_decide.

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_propose"
  }
}

Input Schema

NameRequiredDescriptionDefault
rootNoProject path or workspace root.
confirmNoMust be true to persist proposals; has no effect on read-only generation.
persistNoWrite the generated packet to proposals.json; false returns it without changing project state.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.13.2
    • changedInput schema / properties / confirm / description
      Previous value: -"Required when persist is true."New value: +"Must be true to persist proposals; has no effect on read-only generation."
    • changedInput schema / properties / persist / description
      Previous value: -"Persist proposals.json in the project."New value: +"Write the generated packet to proposals.json; false returns it without changing project state."
  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 safety burden and does so well: it discloses that proposals are never auto-activated, that the result includes evidence, questions, freshness, and persistence status, and that persisted proposals still need an explicit decision. It does not state whether persisting overwrites an existing proposals.json or what permissions are required, which is a residual gap for a tool with a write mode.

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 sentences, front-loaded with the core action, followed by usage context and the safety caveat. Every sentence adds information with no repetition of the title or schema.

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?

There is no output schema, and the description compensates by enumerating what the result packet contains (evidence, questions, freshness, persistence status). Combined with the no-auto-activation caveat, an agent has enough to call it correctly, though the shape of the returned packet remains somewhat abstract.

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, and persist are already fully documented with their defaults and effects. The description does not add syntax or interaction detail beyond the schema, so the baseline of 3 applies.

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 ('Generate evidence-backed candidate architecture rules and contracts from the current project model'), which distinguishes it clearly from the decision-oriented sibling codapult_guard_proposal_decide. An agent can tell immediately that this tool produces proposals rather than acting on them.

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 triggering situation ('after setup or structural changes'), the exclusion ('proposals are never activated automatically'), and routes the follow-up decision to the named sibling codapult_guard_proposal_decide. This is explicit when/when-not/alternative guidance.

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