evaluate_events

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

With no annotations provided, the description carries the full burden. It goes beyond the obvious by explaining the engine selection behavior: 'Detection-only rules use the stateless engine; collections with correlations use the stateful correlation engine.' This is valuable behavioral context. It also mentions optional `pipelines` and `match_detail`, hinting at configurability. It doesn't mention side effects or return format, but given it's a pure evaluation tool, the key behavioral trait is covered.

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 three sentences, each earning its place: first sentence states purpose, second explains engine behavior, third covers inputs and options. It is front-loaded with the most important information and contains zero filler. This is an exemplary level of conciseness for a tool with 9 parameters.

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 (9 parameters, mutual exclusions, stateful/stateless engines) and the absence of an output schema, the description is quite complete. It covers the core input mechanisms, the engine dichotomy, and optional settings. However, it doesn't outline the expected return structure beyond 'matches,' which could be ambiguous for a tool with no output schema. A bit more detail on response format would make it fully complete.

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?

Schema description coverage is 100%, so the baseline is 3. The description repeats the main input methods (yaml/path, events/events_path) but adds no new semantic detail beyond what the schema already provides. It does group the parameters into logical pairs, which is helpful, but it doesn't compensate for any missing schema information because none is missing.

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 tool's purpose: 'Evaluate JSON events against Sigma rules and return matches.' The verb 'evaluate' and resources 'JSON events' and 'Sigma rules' precisely define the operation. It distinguishes itself from sibling tools like lint_rules or validate_rules, which focus on static analysis, whereas this tool executes rules against events.

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 context on how to use the tool ('Rules via inline `yaml` or `path`; events via an inline `events` JSON array or an NDJSON `events_path`') and explains when different engines apply (detection-only vs stateful correlation). It doesn't explicitly name alternative tools for exclusion, but the strong purpose clarity makes the intended use implied. This earns a 4 rather than a 5 because there is no explicit 'when not to use' guidance.

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