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

Beyond the annotations (readOnlyHint false, destructiveHint false, idempotentHint true), the description adds important behavioral context: it is a paid workflow ($0.25 or free-tier quota), includes conditional triage triggered by high/critical risk, produces a signed receipt and 30-day record, and explicitly warns that triage does not imply human approval. This gives the agent a clearer picture of side effects and caveats.

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 two sentences, with the purpose and key components front-loaded in the first sentence. It efficiently conveys the workflow, cost, and a critical caveat without wasted words. The colon structure organizes the components cleanly.

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?

Given the tool's complexity (16 parameters, output schema present, multiple workflow stages), the description provides a solid high-level summary. It explains the conditional triage, payment options, and the duration of the status record. The presence of an output schema covers return-value details, so the description does not need to list them. Minor gaps include lack of explicit description of the decision values or failure modes, but overall it is sufficient.

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?

The input schema has 16 parameters with 100% description coverage, so the baseline is 3. The tool description does not add parameter-level meaning beyond what the schema already provides, but it also does not need to given the high schema coverage. The high-level workflow description indirectly references some concepts (e.g., evidence, triage) but does not map them to specific parameters.

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 clearly identifies the tool as 'Complete AI agent action safety workflow' and enumerates the specific steps it performs: DestructGuard evidence, conditional ReviewQueue triage, decision, signed receipt, and a 30-day status record. This distinguishes it from the sibling 'action_safety_quick_gate' by emphasizing completeness, and the verb 'workflow' implies execution.

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 implies usage via the 'complete workflow' phrasing and the cost/payment context, suggesting it is the full pipeline as opposed to faster or partial alternatives. However, it does not explicitly state when to use this tool versus siblings like 'action_safety_quick_gate' or sub-step tools, nor does it provide exclusion criteria.

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