List DLP risks

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

Annotations already declare readOnlyHint=true, covering safety. The description adds behavioral detail beyond that by explaining the default summary mode and its data sources ('by_user from Analytics/Overall; by_rule/by_day/sample from Risks/Overall2') and what 'raw' means. It does not describe return formatting, but an output schema exists, so that is not a required gap.

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 short and well-structured: a one-line purpose, a 'Use for' line, a default-mode note, and a 'Not for' line. Every sentence earns its place, and the most important scoping information is front-loaded.

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 a 10-parameter tool, 80% schema coverage, an output schema, and annotations, the description provides a strong selection and invocation context. It names alternatives and defaults, but does not clarify the semantics of compact and fetch_all, which are the two parameters without schema descriptions; this leaves a minor gap for fully-informed invocation.

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 80%, so most parameters are already documented. The description adds meaning by explaining mode semantics: 'summary' produces by_user/by_rule rollups and 'raw' maps to the Risks/Overall2 page. This goes beyond the schema's own enum labels, though the undocumented compact and fetch_all parameters are left to inference.

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 a specific verb and resource: 'List or summarize DLP/rule Risks for a period.' It further clarifies scope with 'Use for: policy/keyword/USB/AI rule hits' and explicitly differentiates from siblings by saying it is 'Not for idle time (get_idle_summary) or timetable deviations (list_anomalies).' This makes the tool's purpose unambiguous and distinguishable.

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 gives explicit selection criteria with 'Use for' and 'Not for', naming the exact alternatives (get_idle_summary and list_anomalies). It also states the default mode ('Default mode=summary'), providing clear guidance on how to invoke the tool in its most common form.

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