sat_ground_track

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

No annotations exist, so the description bears the full disclosure burden, and it does partially carry it: the output is an image, out_px caps at 2048, minutes caps at 1440, step floors at 0.5, and the agent is told to surface the returned link verbatim because images may not render. It does not say what happens when a name fails to resolve, whether TLE data is fetched live or cached, or what errors look like.

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 first line front-loads the purpose and the return type, examples follow immediately, and the Args block is dense with no filler. The closing instruction about presenting the link is short and operationally necessary rather than padding.

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 no-annotation, no-output-schema tool with six parameters, the description covers output form (image plus link), parameter caps, defaults, and name-to-ID resolution behavior. It stops short of documenting failure modes for unresolvable satellite names or confirming whether data is fetched in real time, which for a 'now'-style tracking tool an agent would want to know.

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?

With 0% schema description coverage, the description fully compensates: all six parameters are explained with examples, defaults, ranges, and a clear precedence rule (norad_id overrides name), plus a non-obvious hint tying minutes to QZSS orbit shape. The only friction is that step is typed integer in the schema while the description states a 0.5-minute minimum, a minor inconsistency that does not obscure intent.

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 a specific verb and resource: it plots a satellite's current position and ground track onto an Earth map as an image, and gives three concrete query examples (ISS, Hinode, Hubble). What an agent gets back is unambiguous, but the description never names or contrasts a sibling such as sat_tle, iss_now, or sky_map_with_satellites, so routing still requires inference.

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 natural-language example queries imply when the tool applies, and the guidance that a QZSS figure-eight orbit needs about 720 minutes is a genuinely useful usage tip. However, there is no explicit statement of when NOT to use it or which sibling to prefer for raw TLE data versus a rendered map, and no prerequisite information is given.

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