Start Investigation

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

Annotations already declare that this is a non-read-only, open-world, non-idempotent operation, so the description does not need to restate that. It adds useful workflow context by implying an asynchronous run that should be followed with get_investigation_progress, though it omits failure modes such as rerun_unavailable.

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 short sentences, front-loaded with the main action and followed by the required next step. There is no wasted wording.

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?

With rich schema coverage, annotations, and an output schema, the description supplies the key operational context: what it starts and which tool to call next. It leaves detailed rerun constraints and failure behavior to the schema, which is acceptable but slightly incomplete for a starting operation.

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%, so the schema already documents alert_id, incident_id, and rerun behavior in detail. The description only implies that one of alert or incident should be chosen, without adding meaning beyond the schema for rerun.

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 states a specific verb and resource: starting an AI SRE investigation on one alert or incident. It also names the follow-up sibling get_investigation_progress, making the action distinguishable from read/list investigation tools.

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?

It clearly indicates the trigger context: use it on one alert or incident, then follow with get_investigation_progress. It does not explicitly cover when not to use it versus list_investigations or get_investigation, nor when rerun should be used.

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