detect_bill_anomalies

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

With no annotations, the description carries the full burden and does substantial work: it discloses local-only processing ('nothing is sent anywhere'), the detection method (each service compared against its own recent normal), the event types (spikes, drops, new spend), the ranking criterion (excess cost), and that ongoing events are flagged. It omits failure behavior for malformed/non-FOCUS CSVs and says nothing about output volume relative to `limit`.

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 dense sentences with the capability and its trust/privacy property front-loaded, followed by a compact use-case list. The parenthetical about local CSV is justified because it answers a prerequisite question, though the sentence is long enough to be slightly harder to scan than necessary.

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?

For a 5-parameter tool with no output schema, the description explains inputs, method and ranking but leaves the `sensitivity` knob and the event payload structure undocumented, and never states that the CSV must conform to FOCUS 1.x or what happens when it does not. Adequate to call correctly in the default case, incomplete for tuning or troubleshooting.

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 only 40%, so the description must compensate, and it partially does: 'ranked by excess cost' explains the ordering behind `limit`, and 'each service's ... cost' aligns with the default group_by=ServiceName. However, the `sensitivity` enum (strict/moderate/permissive) is never explained anywhere, and neither `group_by` alternatives nor `limit` semantics are addressed in the description.

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?

States a specific verb and resource ('anomaly management on the user's actual bill') and pins the data source as a local FOCUS 1.x CSV export, which clearly separates it from price-level siblings like detect_price_anomalies or get_price_history. It stops short of naming that sibling explicitly, so the differentiation is inferable rather than stated.

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?

Three concrete example questions ('what blew up our bill', 'did anything unusual happen last week', 'what new spend appeared') give an agent a strong selection signal and imply the anomaly-detection scope. There is no when-not-to-use clause and no named alternative (e.g. analyze_bill or detect_price_anomalies), so an agent must infer the boundary.

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