record_incident

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

With no annotations provided, the description carries the behavioral burden. It discloses a persistent write to the action ledger, enforces validation ('evidence' must reference existing ledger seqs), and explains the default behavior of 'aware_ts'. It could add more about permissions or reversibility, but the key behavioral constraints are usefully exposed.

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 dense sentences, front-loaded with purposeebab and immediately followed by the operational rules. Every sentence earns its place, and backticked parameter names make the syntax scannable.

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?

The description covers the core invocation needs and important domain rules, but with 7 parameters)Skip and no output schema, it leaves several gaps: exact severity enum values are only implied, 'subject' is not explained, and the return/acknowledgment behavior is not described. Adequate yet short of 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 0%, so the description must add meaning. It does this well for severity (reporting deadlines), evidence (must exist), and aware_ts (default now). A few parameters like 'subject' and 'actor' are left implicit, but the most consequential parameters are given domain-specific semantics beyond the schema.

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 names a specific action ('Record') and a specific resource ('serious incident in the action ledger'), reinforced by the legal context (EU AI Act Art. 73). This clearly differentiates it from sibling tools like incident_reported and incident_report, which sound like queries rather than write operations.

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 gives a clear usage context: record incidents that fall under EU AI Act Art. 73, with severity determining the reporting clock. It does not explicitly name alternatives or exclusion conditions, but the trigger conditions (serious incident, severity categories) are specific enough for an agent to know when this tool applies.

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