investigate_incident

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

Without any annotations, the description carries the full burden of behavioral disclosure, and it does well: it reveals that the tool consults episodic memory, invokes an LLM to plan tool calls, queries logs/metrics/runbooks, waits by default, and returns a report. It does not in the description disclose the ticket-creation/memory-write side effects implied by dry_run, but the schema covers that and there is no contradiction.

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?

Two sentences with no wasted words: the first states the primary action and pipeline, the second states default wait behavior and return value. It is front-loaded and every clause earns its place.

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 complex orchestrator with no output schema, the description covers the main workflow, default waiting, and the return value, which is enough to call the tool correctly. A minor gap is the lack of explicit mention of the task_id path when wait_seconds=0 and the ability to poll via get_investigation, though the schema does document the immediate-return behavior.

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 100%, and the schema itself provides strong descriptions for goal, context, dry_run, and wait_seconds, including an example and side-effect clarifications. The description adds no per-parameter detail beyond the schema, so the baseline of 3 is appropriate.

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 opens with 'Run an AgentCore incident investigation' and then breaks down exactly what that entails: retrieving similar past incidents, planning tool calls with an LLM, querying logs/metrics/runbooks, and synthesizing a report. This clearly differentiates it from sibling tools like get_investigation, search_incident_memory, and export_postmortem, which focus on retrieval/export rather than running a full investigation.

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 makes it clear this tool is for starting a new investigation and returning a synthesized report, including the default blocking behavior. It does not explicitly name alternatives or say 'use get_investigation if you already have a task_id', but the purpose is clear enough for an agent to select it appropriately.

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