nemesis_omniguard_score

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

The description adds important behavioral context beyond the annotations: it discloses the dry_run default (no metering/persistence), the need for specific credentials, and the expected risk signals. This goes beyond the readOnlyHint/openWorldHint/destructiveHint flags, though it doesn't detail live-mode side effects beyond what the schema notes.

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 concise and well-structured: it leads with the purpose, then the default behavior, then dependencies, and finally input guidance. Every sentence serves a clear function with no redundant or vague filler.

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 tool with a nested transaction object, no output schema, and moderate complexity, the description covers the key aspects: what it does, how to invoke it, what inputs are expected, and the default safety mode. It could be more explicit about the exact response format, but the allow/review/block outcome is implied.

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 all parameters with descriptions (100% coverage), but the description enriches the 'transaction' object by listing the key risk signals (amount, country vs card_country, card_type, etc.) that the rules check. This adds meaning beyond the schema's example.

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 action ('Score a transaction against an Omniguard function') and the result categories (allow/review/block). It is specific and uses a distinct verb, but it does not explicitly differentiate from sibling tools or name an alternative for similar tasks.

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?

The description provides clear usage context: it is for testing business-logic rules end to end, defaults to dry_run, and notes the prerequisite of having an ingest token and function ID from nemesis_create_omniguard. It does not explicitly state when not to use this tool or mention alternative tools for other scenarios.

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