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

The annotation already declares readOnlyHint=true, and the description reinforces it with 'READ-ONLY: this call changes nothing and can be repeated safely.' Beyond the annotation, it discloses a critical behavioral nuance: the 'mod_state' column is retroactively mutable unless pinned to an event id. This adds real value by warning the agent about data stability. It does not mention other behaviors (rate limits, auth), but given the read-only annotation, this is adequate. No contradiction with annotations.

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 two sentences with zero waste. The primary purpose and default behavior are front-loaded, followed by the critical stability warning and the read-only note. Every sentence contributes useful information without repetition.

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 simple read-only tool with two optional parameters and no output schema, the description covers the essential context: what it returns (the moderated set), how to pin it, the stability warning, and safety. It doesn't describe the output format, but that is not explicitly required here since the response is implied. It also doesn't mention any prerequisites or error conditions, but for a read-only snapshot these are less critical. Overall, it is complete enough for an agent to call correctly.

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?

The schema has 50% description coverage (through_event is labeled 'Legacy alias', through_event_id has no description). The description adds meaning to through_event_id by explaining it is the parameter that pins to a specific point in the log and defaults to latest. However, it does not explain the relationship between through_event and through_event_id beyond the schema's alias hint, and it doesn't explicitly warn that through_event is deprecated. The description partially compensates for the coverage gap but leaves ambiguity about the legacy 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 states a specific verb ('get the moderated set'), a resource ('moderation state'), and a precise temporal qualifier ('as of a point in the moderation log'). It distinguishes itself from the sibling 'moderate' (which is likely the mutation) and clarifies the core function: a read-only snapshot that can be pinned to an event id. This is a clear, non-tautological purpose.

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 explains when to use this tool: when you need the moderation state at a specific point in time, and it warns about the default behavior (latest event). It also explains why pinning to an event id is beneficial ('reproduces forever instead of changing under you tomorrow'). It does not explicitly name an alternative, but no direct sibling serves the same purpose, so this is sufficient. A small gap: it doesn't say when NOT to use it (e.g., if you need the full history), but this is minor.

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