evtx_export

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

With no annotations, the description carries the full burden and does add real behavioral facts: a unique file, a SHA-256 digest, and the crucial distinction that preview clipping does not discard file rows while scan/row caps mark the export incomplete. It still omits error/failure behavior, permission expectations, and what 'unique 0600, no overwrite' (only in the schema) implies operationally.

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 tight sentences with the primary action front-loaded and no filler. The density is near the edge of cryptic, but each clause (SHA-256, bounded preview, cap vs clip semantics) carries distinct information.

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?

An output schema exists, so return values needn't be explained, and the export/artifact semantics are covered. For an 18-parameter tool with a nested where object and heavy time-range filtering, the description still leaves filtering and predicate behavior to the schema alone.

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 only 44% across 18 parameters, so the description should compensate more than it does. It clarifies the interplay of scan/row caps and the preview budget, but leaves the filter surface (contains, not_contains, event_ids, provider, start_time/end_time, where) without additional meaning beyond what the schema already says.

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?

States a specific verb (persist/export) and resource (selected EVTX matches) plus the artifact produced (a unique JSONL file with SHA-256 and a bounded preview). The word 'persist' implicitly distinguishes it from evtx_search-style read-only siblings, though no sibling is named explicitly.

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?

There is no statement of when to prefer this over evtx_search, evtx_security_search, or evtx_get_event, nor any prerequisites. The phrase 'all selected matches' hints the tool consumes filters established elsewhere, but the agent gets no explicit routing guidance.

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