Skip to main content
Glama

alignment_gate

Read-only

Run an AI system prompt (and optional agent config) through a 45-criterion alignment/safety rubric. Returns a letter grade (A-F), numeric score, per-flag remediation, and a pass/fail verdict.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "system_prompt": "<system_prompt>"
    },
    "name": "alignment_gate"
  }
}

Input Schema

NameRequiredDescriptionDefault
model_idNoOptional target model identifier.
agent_configNoOptional agent config (tools, memory, temperature, etc.). Any JSON object; it is serialized and only the first 2,000 characters reach the rubric.
system_promptYesThe system prompt text to evaluate.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / agent_config / additionalProperties
      Added value: +{
      +  "description": "Any JSON value."
      +}
    • changedInput schema / properties / agent_config / description
      Previous value: -"Optional agent config (tools, memory, temperature, etc.)."New value: +"Optional agent config (tools, memory, temperature, etc.). Any JSON object; it is serialized and only the first 2,000 characters reach the rubric."
  2. First observed

TDQS

A3.6/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnlyHint=true, destructiveHint=false, openWorldHint=true, idempotentHint=false), so the bar is lower. The description adds real value beyond them by disclosing the entire output contract (grade A-F, numeric score, per-flag remediation, pass/fail verdict) and the rubric's 45-criterion scope, which is the only source of return information since there is no output schema. It stops short of saying whether grading is deterministic or costly to run.

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?

Two sentences, zero padding, with the operation stated first and the return shape second. Every clause earns its place and nothing is repeated from the schema or annotations.

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 3-parameter, non-destructive scoring tool with a fully described schema and no output schema, the description supplies both the scope (45 criteria) and the return values, which is what an agent most needs. Remaining gaps are minor: no note on runtime cost, determinism of the grade, or what happens if the prompt fails the gate.

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%, including the important detail that agent_config is serialized and only the first 2,000 characters reach the rubric, so the schema carries parameter meaning. The description only echoes 'optional agent config' and adds no format or interaction detail, so baseline 3 applies.

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?

Names a specific verb and resource: 'Run an AI system prompt ... through a 45-criterion alignment/safety rubric', plus the return contract (letter grade, numeric score, per-flag remediation, pass/fail). That is unambiguous on its own, but it never distinguishes itself from grading-style siblings such as humanizer_score, readability_grade or acceptance_criteria_validator.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no explicit when-to-use guidance, no prerequisite or exclusion, and no pointer to an alternative tool. An agent can infer that this is a pre-deployment prompt audit, but nothing tells it when to choose this over the other scoring tools in the sibling list.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.