Fast yes/no guardrail verdict — returns only ALLOWED or BLOCKED with no proof details. Use when you need a lightweight gate and don't need the full SAT/UNSAT report or ZK proof. Same formal verification under the hood, just a minimal response. 1 credit. Requires api_key.
| Name | Required | Description | Default |
|---|---|---|---|
| action | Yes | The agent action to check (max 2000 chars) | |
| api_key | Yes | Your ICME API key | |
| policy_id | Yes | Policy ID from make_rules |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the burden. It discloses that the response omits proof details, that it uses the same formal verification under the hood, and mentions credit cost and api_key requirement. It could add more about error behavior or response format beyond ALLOWED/BLOCKED, but the key behavioral trait—minimal response—is clearly disclosed.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is five sentences and front-loaded with the core purpose ('Fast yes/no guardrail verdict'). Each sentence adds value: minimal response, use cases, same verification, credit cost, and key requirement. No fluff.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has 3 required params, 100% schema coverage, no output schema, and no annotations, the description competently fills gaps: it clarifies the minimal response type, cost, and alternative. It lacks an explicit output schema but the 'returns only ALLOWED or BLOCKED' statement effectively covers the return format. Slight deduction for not mentioning pagination or error cases, but not critical for such a simple tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already covers 100% of parameters with descriptions, so the baseline is 3. The description adds minimal parameter value beyond the schema, but it mentions 'action' as the agent action to check and 'policy_id' from make_rules, which reinforces the schema. No extra syntax or constraints are added.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('returns') and resource ('yes/no guardrail verdict') while clearly distinguishing itself from siblings that return full SAT/UNSAT reports or ZK proof. It explicitly states the minimal response type (ALLOWED/BLOCKED), making the purpose unmistakable.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It explicitly states when to use: 'Use when you need a lightweight gate and don't need the full SAT/UNSAT report or ZK proof.' It also contrasts with the alternative (full report tools) and specifies a cost (1 credit) and auth requirement, guiding invocation.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool has a distinct role, but the presence of payment-method variants (check_action vs check_action_paid, create_account vs create_account_card, top_up vs top_up_card) introduces minor overlap that is clearly explained. The check tools are differentiated by output detail and purpose, though quick_check and check_action could be confused at a glance.
Names predominantly follow a verb_noun pattern (check_action, create_account, run_tests), with consistent _paid and _card suffixes for payment variants. Minor deviations like quick_check (adjective_noun) and top_up (phrasal verb) are understandable but break the pattern slightly.
With 14 tools, the set covers the full lifecycle of policy creation, testing, action checking, payment, and proof verification without bloat. Each tool serves a clear purpose within the service's scope.
The primary workflow (create policy, test policy, check actions, verify proofs) is well covered, including multiple payment options. Missing utilities like listing or deleting policies and credit balance checks are minor gaps that don't block the core use case.