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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, and the description adds real context beyond them: a 48-hour prediction horizon, the verdict taxonomy (compatible / contradicted / untestable / under review), and a privacy guarantee ('public data only, no personal information'). It stops short of describing result volume or ordering, but the output schema covers return shape.

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?

Two dense sentences followed by a short privacy clause; the scope and time window are front-loaded and the sibling routing follows immediately. Nothing is repeated from the title and no sentence is 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 zero-required-parameter list tool with a full output schema and complete annotations, the description supplies everything an agent needs to pick it: scope, time window, content taxonomy, privacy posture, and explicit alternatives. Return values are correctly left to the output schema.

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 clear enum descriptions for kind and lang, so the schema does the heavy lifting. The description's framing of the two event families implies what 'prevu' vs 'signale' return, but it adds no syntax, defaults, or guidance for lang/limit — the baseline 3 applies.

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 verb and resource ('List Vigi-Sky's sky events') plus the two concrete content types — predicted ISS/Starlink passes for the next 48 hours and clustered witness reports with verdict classifications. It immediately distinguishes itself from the adjacent pass-lookup and sighting-identification siblings.

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?

Gives an explicit selection rule ('Use it for what happened or will happen in the sky') and names both alternatives with the condition that routes to each: iss_city_passes for one city's passes, what_did_i_see for one past sighting. No inference required.

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