record_corrective_action

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

With no annotations, the description carries the full burden and provides meaningful behavioral detail: it enumerates the parties that may be informed, states that refers_to entries must exist, and discloses that the returned report names uninformed parties. It does not spell out mutation/persistence side effects, but the verb 'record' plus these constraints gives adequate transparency.

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, front-loaded, and free of filler; each clause maps to a specific schema property. The semicolon-separated format is scannable despite the length, and the legal context is stated once without repetition.

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 most domain semantics and gives a partial output signal via the uninformed-parties report, which is helpful given there is no output schema. However, the missing explanations for actor (required) and causes, combined with no annotations, leave the tool not fully self-sufficient for an agent.

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 compensate. It explains kind, non_conformity, refers_to, informed, and presents_risk, but omits the required actor parameter and the optional causes parameter, leaving their meaning to inference. That is a meaningful gap for correct invocation.

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 opening phrase 'Record a corrective action (EU AI Act Art. 20)' names a specific verb, object, and legal context, and the field-level details distinguish it from sibling tools like record_incident and record_risk. There is no ambiguity about what resource this tool operates on.

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 clear conditions for how to populate fields and when authority notification is required, but it never explicitly says when to use this tool versus alternatives such as record_incident or corrective_action_report. Usage context is implied by the name and Art. 20 reference rather than stated directly.

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