Hunt (TLQL)

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so safety is well covered. The description adds useful behavioral context beyond annotations: it discloses the index size (~106k rows), deterministic nature, the distinction between stats vs row-returning modes, and the default/max limit behavior. This adds meaningful value beyond what annotations and schema provide.

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 dense but efficient—each sentence earns its place. It packs purpose, usage guidance, alternatives, syntax example, and operational details into a compact block. No filler or redundancy; the stats-append instruction and hunt_schema callout are practical and precise.

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?

With a rich output schema present, an idempotent non-destructive profile from annotations, and 100% parameter schema coverage, the description covers the remaining gaps well: when to use it, syntax, aggregation behavior, limit semantics, and the prerequisite schema lookup. For a query-language tool of this complexity, it is 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 coverage is 100% (both limit and query parameters have descriptions), so the baseline is 3. The description adds value by explaining the TLQL syntax with a concrete example, clarifying how stats mode works, and noting the limit row cap is ignored in stats mode—context beyond the schema's parameter descriptions.

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 this is a deterministic SIEM-style query tool over a pre-joined observation index, with an explicit verb, resource, and scope. It also distinguishes itself from siblings by naming the alternative (chaining search_threats calls) and specifying when to use it instead, plus giving a concrete example query.

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?

Explicit when-to-use guidance is given (aggregate questions, cross-observation-type questions), with the explicit alternative ('use INSTEAD of chaining many search_threats calls'). It also instructs calling hunt_schema first if field names are unknown, which is a clear prerequisite. The description explains the stats-mode behavior and how to trigger aggregation.

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