anomalies

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 the composition of the response and the threat_level vocabulary (low|elevated|high) plus a numeric score. It says nothing about cost or latency for a multi-source fusion call, whether the call is read-only, or how 'recent' is bounded. Useful output context, but material behavioral facts are absent.

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?

One dense sentence, front-loaded with the purpose and the scope rule before the payoff list. Every clause contributes content. The only slight inefficiency is the length of the enumeration, which could be collapsed, but nothing is genuinely wasted.

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 structure need not be spelled out, and the description does sketch the payload categories. However, for an 8-parameter geospatial tool with zero schema descriptions and no annotations, the caller gets no help on bounding-box vs radius semantics, what 'detail' changes, or the call's cost profile — gaps that directly affect correct 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 0% across 8 parameters, so the description is the only source of parameter meaning — and it only conveys the lat/lon-vs-global case. It says nothing about radius_nm (default 500), the detail setting, or the min/max_lat/lon bounding box, nor how a bbox interacts with a center point plus radius. That leaves most of the parameter surface undocumented in both places.

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 names the resource (a fused anomaly report) and enumerates its contents: emergency aircraft, GPS-jamming hotspots, dark-vessel candidates, fusion alerts, plus threat_level and score. That is far more specific than a label like 'anomalies' and implicitly separates it from single-domain siblings such as gps_jamming or aircraft_density. It stops short of explicitly naming an alternative, so it sits at 4 rather than 5.

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 parenthetical '(or global if no coords)' gives one concrete selection rule: supply coordinates for a local scan, omit them for a worldwide one. Beyond that there is no guidance on when to reach for this fused report versus whats_changed, area_baseline, or get_situation, and no stated exclusions. Usage is implied by the scope clause rather than taught.

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