area_baseline

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

With no annotations, the description carries the full burden, and it does disclose one important trait: global requests use the background sampler while an AOI baseline only accumulates through repeated polling — implying warmup and possibly thin-baseline results early on. It leaves out whether lat/lon must be supplied together, what happens on a first AOI call with no history, and any cost/latency implications of repeated polling.

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?

Roughly four short sentences, front-loaded with the decision question the tool answers, then the metric list, then operating notes. There is no filler; density is high for the length. Minor cost: the mode/baseline sentences read slightly compressed and could be ordered more explicitly.

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?

An output schema exists, so return formatting needn't be described, and the description supplies the analytical framing plus the baseline-accumulation caveat. For a 4-parameter statistical tool with no annotations, though, an agent still lacks guidance on radius units, what `detail` changes, coordinate pairing, and behavior when a baseline is too sparse to z-score.

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 0%, so every parameter depends on the description. It partially compensates for lat/lon by explaining the global (background sampler) versus AOI (repeated polling builds baseline) distinction, which clarifies the meaning of null coordinates. However `radius_nm` (units/range/default of 500) and `detail` (default "short", presumably output verbosity) are never mentioned, leaving half the parameter surface undocumented.

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 analytical product: current vessel / dark-vessel / jamming / military counts z-scored against a rolling baseline with anomalies called out, framed by the question "Is this normal?". The resource (AOI activity counts vs. baseline) is concrete and distinct from a plain count or listing tool. It stops short of naming how it differs from siblings like `anomalies`, `get_situation`, or `whats_changed`, leaving the agent to infer the boundary.

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?

"Distinguishes a real shift from a normal day" gives a clear selection criterion for when to reach for this tool instead of raw counts, and the note about global vs. AOI baselines tells the agent which mode to pick. It does not explicitly exclude alternatives (e.g. when to prefer `anomalies` or `whats_changed` instead), so it falls short of full when/when-not guidance.

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