defensetech_audit_event_check_invariants

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

With no annotations, the description carries the full burden and does well: it declares the checks are deterministic, discloses the return shape (ok + errors + passed), and explicitly bounds the tool as 'not a legal compliance determination.' It stops short of saying what happens on missing/invalid input or whether any auth is required.

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?

Three tight sentences, front-loaded with the action and the three checks, then the field caveat, then the return/disclaimer. Every sentence earns its place with no 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 nested-object input with zero schema documentation and no output schema, the description covers the return shape and one required field but leaves the structure of the event object largely unexplained. An agent still cannot determine which other event fields feed the CUI and ITAR checks, a notable gap given the complexity.

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 0% and the single 'event' parameter is an unspecified nested object, so the description must compensate. It adds genuine field-level meaning by naming event.discovered_at as required and clarifying event.timestamp is not a substitute, but it documents only one field of an otherwise opaque nested object containing CUI/ITAR/interval data.

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 action (run checks) and enumerates exactly the three deterministic checks performed, each of which maps to a sibling tool (defensetech_check_cui_distribution_statement, defensetech_check_itar_us_person, defensetech_check_dfars_72h_clock). An agent can tell this is the composite bundle versus the individual check tools without opening any schema.

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 enumeration of all three sub-checks implicitly signals that this is the bundled entry point, but the description never states when to use this tool versus calling the three individual sibling checks, nor any prerequisites or exclusions. Usage is inferable but not spelled out.

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