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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=true, so the safety and externality profile is covered. The description adds useful provenance (CelesTrak) and states that orbital elements are returned, but it leaves the surprising idempotentHint=false unexplained — an agent would want to know whether repeated identical queries can return different result sets.

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?

A single tight sentence with no filler, and the resource plus filter are front-loaded. It is arguably too terse rather than padded, but nothing in it is 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?

For a tool with three required, fully undocumented parameters and no output schema, the description should have specified valid 'kind' values (e.g. catalogue groups), what 'name' matches (satellite, group, or operator), and what the orbit payload looks like (TLE lines vs. Keplerian elements). None of that is present, so an agent cannot call it correctly without trial and error.

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% for all three required parameters, so the description must compensate and largely does not. It vaguely maps 'kind' and 'name' but frames them as alternatives ('by kind or name') while the schema requires both, and it says nothing at all about 'limit' (max results? page size? units?). This leaves the agent guessing on every 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?

Identifies the resource (active satellites), the upstream source (CelesTrak), the filter dimensions (kind or name) and that orbital data is included. It is distinguishable from siblings like cell_sensor_iss or cell_sensor_launches because it implies a general catalogue rather than a single object. The verb is implicit (fetch/list) rather than stated, which keeps it just short of a 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?

There is no guidance on when to choose this over cell_sensor_iss, cell_sensor_launches, or cell_sensor_sondes, and no mention of prerequisites or rate/refresh considerations for a live external feed. The only usage signal is the phrase 'by kind or name', which is ambiguous about whether the two are alternatives rather than both required.

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