bi_audit_actions

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

The description goes far beyond the readOnlyHint annotation by explaining the audit algorithm, the cohort bucketing, the '<CAM>' path templating to avoid false positives, and the separate 'disabled_outliers' reporting. It also warns that outliers are not necessarily bugs and clarifies that there is no live BI connection. This is rich behavioral disclosure with no contradiction against annotations.

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 long but each sentence earns its place: purpose, methodology, false-positive avoidance, output organization, and user-handling guidance are all useful. It is front-loaded with the core purpose and only then dives into mechanics. Slight redundancy around 'informational' and 'pure read' is minor.

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?

There is no output schema, so the description carries the burden of explaining return behavior; it names the output keys ('outliers', 'disabled_outliers', 'unbucketed') and clarifies how outliers should be interpreted. It also covers the tool's read-only nature, the data source, and appropriate user interaction. No critical operational detail appears to be missing for an agent to call it correctly.

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 coverage is 100%, so the baseline is 3. The description adds general context about cohorts and modal values, which relates conceptually to min_cohort, but it does not add parameter-level meaning beyond what the schema already provides. This is adequate given the schema already documents each parameter.

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 precise verb and resource: 'surfaces cross-camera action-row outliers' by walking each camera's .reg export and bucketing action rows into cohorts. It clearly identifies what the tool does and why, and the mechanics distinguish it from simple getter tools like bi_get_actionset or bi_list_alerts. It is not a tautology and states a specific analytical purpose.

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 clear context for when to use the tool: when the user needs to review cross-camera action-row divergences, and it explicitly instructs the agent to present findings as 'values worth confirming' and ask whether each is intentional. It does not explicitly name alternative tools or list exclusion criteria, but the use case is clearly scoped as an informational audit rather than a live query.

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