Update an existing custom rule. Requires API key (Pro+).
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | Rule ID to update | |
| name | No | ||
| tier | No | ||
| severity | No | ||
| description | No | ||
| detection_pattern | No | There is no 'pattern' field — 'detection_pattern' is the only field name the evaluator reads; the backend explicitly rejects 'pattern'. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are available, so the description must disclose behavioral traits. It mentions the API key requirement, which is useful, but fails to indicate whether updates are partial or full, what fields are affected, or any side effects. The schema contains a critical note about 'detection_pattern' being the only accepted field name, but the description omits this important behavioral detail.
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 very concise: two short sentences that immediately state the operation and a requirement. No filler words.
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's complexity (6 parameters, no annotations, no output schema), the sparse description is insufficient. It lacks information about update semantics, param details, and the documented field-name constraint, making it inadequate for an agent to fully infer correct usage.
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 description does not explain any of the six parameters. Schema coverage for descriptions is only 33%, and the description adds no param-level detail, leaving most parameters (name, tier, severity, description) undefined from the text.
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 clearly states the verb 'update' and the resource 'existing custom rule', making it a specific modification operation. However, it does not differentiate from the sibling tool 'update_rules', leaving some ambiguity about individual vs bulk updates.
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 about when to use this tool instead of add_custom_rule, update_rules, or other alternatives. The only additional note is the API key requirement, which is a prerequisite, not a usage recommendation.
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.
Most tools have clearly distinct purposes (e.g., CRUD for custom rules, mode management, presets, validation). However, get_rules, list_custom_rules, and get_rule_modes could be confused since all return rule-related info, though descriptions differentiate their focus.
All tool names follow a consistent verb_noun snake_case pattern (e.g., add_custom_rule, get_audit_log, delete_custom_rule). Even multi-word names like ship_confidence_check maintain the pattern, with no mixing of conventions.
16 tools is slightly above the typical 3–15 range but appropriate for the rule enforcement domain, covering custom rules, presets, modes, audit, and validation. However, three planned-but-unimplemented tools add clutter and could be confusing.
Core operations are present: full CRUD for custom rules, preset application, mode overrides, validation, and audit log. However, three tools are non-functional (NOT_IMPLEMENTED), and there is no way to remove a bypass or manage constitutional rules, leaving some noticeable gaps.