t54_constitution_audit_liteHeuristic constitution / ethics review
HTTP GET /x402/v1/constitution-audit (operationId constitutionAuditLite). Paid routes may return HTTP 402 until the x402 broker settles on the configured rail.
| Name | Required | Description | Default |
|---|---|---|---|
| prompt_snippet | No | Text or agent instruction excerpt to screen for constitution / ethics heuristics (max 4000 chars). |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Output schema / (root)Previous value: -{
- "properties": {
- "result": {
- "title": "Result",
- "type": "string"
- }
- },
- "required": [
- "result"
- ],
- "title": "_dyn_constitutionAuditLiteOutput",
- "type": "object"
-}New value: +nullInput schema / properties / prompt_snippet / descriptionPrevious value: -"Query parameter `prompt_snippet` for operation `constitutionAuditLite` (GET /x402/v1/constitution-audit). max length 4000."New value: +"Text or agent instruction excerpt to screen for constitution / ethics heuristics (max 4000 chars)."Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds the behavioral detail that paid routes may return HTTP 402 until the x402 broker settles, which complements the annotations (idempotent, non-destructive). However, it does not explain whether the tool has side effects (readOnlyHint is false) or what the response contains. Since annotations already cover safety profile, this extra context earns a mid score.
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 brief and front-loaded with the title, then the endpoint and payment note. However, the first sentence is redundant with the title, and the payment note, while relevant, is tangential to purpose. Minimal waste but repetition keeps it from a top score.
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?
For a simple one-parameter tool with no output schema, the description still fails to mention what the response looks like or what 'audit' means operationally (e.g., heuristic pass/fail, scores, citations). The HTTP/402 note is niche and doesn't round out the tool's behavior, making the description incomplete for an agent deciding to invoke it.
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?
Input schema fully describes the single parameter prompt_snippet with its purpose and max length, so the schema carries the semantic load. The description adds no parameter-specific details, but with 100% coverage the baseline of 3 applies.
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 repeats the title 'Heuristic constitution / ethics review' and adds the HTTP endpoint and operationId, but does not explicitly state what action it performs (e.g., screens a prompt for violations) or what it returns. It is distinguishable from sibling tools like contract_audit by the 'constitution/ethics' domain, but the verb/resource combination is vague.
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?
No guidance is provided on when to use this tool versus alternatives such as contract_audit or contract_triage. The only practical note is the payment/402 behavior, which addresses failure conditions, not selection criteria.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.