Search Detections

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

Annotations declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the safety profile is already covered. The description adds value beyond annotations: it discloses pagination behavior (limit default 25/max 200 via offset) and the filter semantics. It doesn't describe the return format, but an output schema exists which covers that. Reasonable balance given the strong annotation coverage.

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?

Two sentences, front-loaded with the core purpose, and packs significant information: search domain (SPL/KQL/Sigma), search dimensions (rule text/technique/threat), filters (type/severity), and pagination (limit default/cap, offset). Zero filler or redundant restating of the tool name.

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 search tool with an output schema, 100% parameter schema coverage, and strong annotations (readOnly, idempotent), the description is complete. It specifies search domains, filters, pagination defaults/caps, and scope. The output schema handles return-value documentation. Nothing meaningful is left unspecified for an agent to execute a correct search.

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 schema already documents all 5 parameters. The description adds value by enumerating the filter dimensions (type, severity, pagination with defaults) and search scope (rule text, technique, threat), providing semantic context like 'keyword search' that ties the parameters together coherently. It slightly exceeds the baseline 3 by framing how type/severity combine with the query.

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 states a specific verb+resource: 'Keyword search across detection logic (SPL/KQL/Sigma) by rule text, technique, or threat.' It clearly distinguishes from siblings like search_vulnerabilities, search_threats, search_iocs, and get_detections (which likely returns all detections without search). The scope (rule text/technique/threat) and optional filters (type, severity) are explicit.

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 implies usage context: search across detection logic by rule text/technique/threat. It doesn't explicitly name sibling alternatives to contrast against, but the type filter (spl|kql|sigma) and severity option provide clear when-to-use context. It doesn't explicitly state when NOT to use it (e.g., use get_detections for unfiltered listing), but siblings with distinct names make this largely inferable.

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