legal_breach_response

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

Annotations already carry the safety profile (readOnlyHint=false, idempotentHint=false, destructiveHint=true), so the description does not need to restate those. It adds some context beyond annotations by disclosing that execution routes through the domain-agent dispatcher under the caller's JWT, tenant, and company scope, which explains the auth and execution model. However, it does not reveal what side effects a destructive breach response entails, whether it runs asynchronously, or whether approvals are involved — for a destructive action this gap matters.

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 compact and well-structured: a one-line invocation statement, a routing line, and a clean Args block. It is front-loaded and avoids padding. It loses one point because the opening sentence largely duplicates the tool name, and the space saved could have carried a real purpose statement.

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 destructive, non-idempotent, open-world action, this is not enough context. The generic dispatcher language could apply to any domain agent action and gives an agent no basis for understanding the breach_response use case, its expected inputs, or its consequences. An output schema exists so return values need not be explained, but the core question — what does invoking breach_response do — remains unanswered.

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 carries the full burden, and it does document both parameters: 'message: Free-text objective' and 'inputs: Optional JSON string of structured inputs.' This adds meaning the schema lacks. However, for an action-specific tool it stops short: the structure of the 'inputs' JSON is unspecified, no allowed keys or examples are given, and the semantics of message beyond being 'free-text' are opaque for the breach_response action.

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 only restates the tool's name — 'Run the legal domain agent action `breach_response`' — without explaining what a breach response actually does. It adds routing mechanics (domain-agent dispatcher, JWT/tenant/company scope) but never clarifies the functional purpose: a breach of what, what the action produces, or what side effects it has. This is essentially a tautology of the name plus infrastructure detail.

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 zero guidance on when to use this tool versus any alternative. The sibling list contains `dispatch_domain_agent`, which appears to be the generic version of the same mechanism, and many legal_* tools, but the description never distinguishes `legal_breach_response` from them or states the triggering condition for a breach response.

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