detect_price_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 disclose real behavior: method is auto-selected by dataset density (percent_change under 5 snapshots, z_score at 5+), and each sensitivity tier maps to explicit thresholds. It omits the return shape of an anomaly record, ordering, and how limit interacts with detection, which keeps it below a 5.

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 core sentences are dense and front-loaded with the detection logic and thresholds, but the closing line about LinkedIn/blog content auto-generation is promotional filler that does not help an agent invoke the tool, and 'Compounds the v0.7.1 history archive' is internal jargon that adds little.

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 five-parameter, no-output-schema tool, the description covers detection methodology well but says nothing about what comes back (anomaly fields, score values, SKU identification) or how limit caps results. Adequate to call correctly, but not complete enough to predict the response.

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 does for the two most ambiguous parameters: 'method' semantics are explained via the snapshot-density rule for auto, and 'sensitivity' is decoded into numeric thresholds (10%/z>=2.5, 5%/z>=2.0, 2%/z>=1.5). 'limit', 'since', and 'cloud' get no added meaning beyond the schema, leaving a partial gap.

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: 'Statistical anomaly detection over the bundled price-history dataset', with the outcome framed as auto-flagging 'unusual price moves' per SKU. An agent can distinguish this from raw retrieval siblings like get_price_history, though it never names those siblings explicitly to sharpen the boundary with detect_bill_anomalies or get_price_history.

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?

Provides concrete triggering queries ('what changed this week?', 'anything weird across any cloud since {date}?') that map directly to invocation, which is strong usage context. It stops short of exclusions or naming alternatives, so the agent must still infer when get_price_history or detect_bill_anomalies is the better choice.

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