Anomaly Scan

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

Annotations already indicate readOnlyHint=true, destructiveHint=false, idempotentHint=true, openWorldHint=true, so the description's claim of 'surface' and 'proactive detection' aligns and adds context that the tool is analytical and non-destructive. No behavioral details are missing or contradictory.

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 immediately conveys the tool's purpose and output. No extraneous words or redundant information.

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 simplicity (2 parameters, no required parameters, output schema exists), the description sufficiently defines purpose and use case. It could optionally mention that results include flagged outliers, but the output schema likely covers that.

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 already contains clear parameter descriptions ('Z-score threshold...', 'Tenant scope...'). The tool's description does not add any further parameter semantics beyond what the schema provides.

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 ('Surface') and clearly identifies the resource ('cost and behavior anomalies'), specifying the kinds of anomalies (per-agent spend, per-session tool-call-rate statistical outliers) and the purpose (proactive runaway-agent detection). This clearly distinguishes it from sibling tools like 'cost_report' or 'tool_risk_assessment'.

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 for proactive detection of runaway agents, but it does not explicitly state when not to use it or provide alternatives. Given the large set of sibling tools, a note on when to prefer this over other scan tools would be beneficial.

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