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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false. The description adds valuable behavioral context beyond annotations: the found=false response when the aircraft is not tracked, the real-time nature of the data, and the no-auth open access. It also explains the source (OpenSky Network). This exceeds the baseline for annotation-covered tools.

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 well-structured and front-loaded with the core purpose, followed by return fields, edge case behavior, and context. It's slightly longer than strictly necessary but every sentence adds value: the found=false explanation, the registration lookup hint, and the source attribution are all useful. No redundant filler.

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 single-parameter read-only tool with an output schema, the description covers the essential context: what data is returned, what happens when the aircraft isn't tracked, how to find ICAO24 addresses, and access requirements. The only minor gap is not explicitly mentioning rate limits or data latency, but these are not critical for a simple lookup tool.

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% with a single parameter (icao24) that has a pattern and example. The description reinforces the parameter by explaining it's the ICAO 24-bit hex address and gives an example (3c6444), but doesn't add substantial meaning beyond the schema. Baseline 3 is appropriate since the schema already fully documents the 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 clearly states the tool gets the current real-time ADS-B state vector for a single aircraft identified by ICAO 24-bit hex address. It lists the specific data fields returned (position, altitude, speed, heading, vertical rate, squawk, origin country, on-ground status) and distinguishes it from sibling tools like opensky.traffic.states_bbox and opensky.traffic.states_country by focusing on a single aircraft lookup.

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 provides clear context for when to use this tool: tracking a specific flight in real time. It also explains the found=false case (aircraft not currently tracked) and how to obtain ICAO24 addresses from registrations. However, it doesn't explicitly name sibling alternatives or state when to use them instead, though the single-aircraft focus implies the distinction.

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