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

Annotations already declare readOnlyHint=true, and the description reinforces this with an explicit READ-ONLY statement plus the non-obvious idempotency/reproducibility property. The note that mod_state is the only retroactively mutable column adds genuine behavioral context beyond the annotation, though return shape and cost are unaddressed.

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?

Three tight sentences with the core semantics front-loaded and no filler. The second sentence is dense but every clause earns its place; slightly more jargon than necessary keeps it from a 5.

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 two-parameter read tool with annotations covering safety and no output schema, the description supplies enough: what is returned, how the point-in-time parameter behaves, and that the call is safe to repeat. Only the composition of the 'moderated set' itself is left undefined.

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 only 50% and through_event_id carries no schema description at all, so the description does useful work by explaining that through_event_id selects a point in the log and defaults to latest. The legacy alias is already covered by the schema, so the added value centers on the temporal semantics.

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 states that this returns the moderated set as of a point in the moderation log, which is a specific resource and a specific temporal scope. It is distinguishable in spirit from the sibling `moderate` (a mutation), though the differentiation is implied rather than named. 'Moderated set' is somewhat jargon-y but workable.

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?

It gives real usage guidance: default to latest, or pin a census to an event id when you need a reproducible snapshot. However, it never states when to prefer this over sibling tools like `moderate`, `rail_census`, or `changes`, and no exclusions are given.

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