start_live_triage

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

With no annotations provided, the description carries the burden of disclosing behavior. It mentions 'background' and 'safety limits', which hint at long-running operation and automatic shutdown, but it does not explain lifecycle details such as how the process is stopped, whether it returns immediately or streams output, or what happens when the anomaly threshold is exceeded. The schema fills some gaps via parameter descriptions, but the main description omits these behavioral traits.

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 a single, well-structured sentence that front-loads the core action and includes important qualifiers without redundancy. Every phrase earns its place: 'background log tailing' defines the resource, 'real-time Z-score anomaly alerting' specifies the alerting mechanism, and 'heap memory safety limits' communicates a key safety feature.

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 tool has no output schema or annotations, so the description must compensate for return behavior and side effects, but it does not explain what happens after start (e.g., job ID, streaming, termination). It sufficiently covers the initiation and key features, but given the complexity of a background monitoring tool, the lack of lifecycle or return information leaves the description incomplete for effective use.

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 covers all three parameters with clear descriptions, so the baseline is 3. The description adds no new syntax or format details beyond what the schema already provides; it merely mirrors the concepts of Z-score alerting and heap memory limits. Thus, it adds little semantic value over the schema.

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 uses a specific verb 'Start' with a clear resource ('background log tailing') and adds key distinguishing features: real-time Z-score anomaly alerting and heap memory safety limits. This clearly differentiates it from siblings like query_log_pattern or detect_error_anomalies, which suggest one-off or batch operations rather than a continuous background process.

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 clearly implies this tool is for live, ongoing monitoring rather than historical queries, giving context for when to use it. However, it does not explicitly state when not to use it or mention alternatives, such as using detect_error_anomalies for batch analysis, so it falls short of offering full usage guidance.

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