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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint, and the description adds meaningful behavioral context beyond that: it never runs a live check, absence of events means no significant moves, and provider-limited or pending engines generate nothing rather than false alerts. This prevents common misinterpretations and fully complements the annotations. No contradiction exists.

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 front-loaded with the core purpose and then adds dense, relevant caveats. The parenthetical event examples justify their length, and there is no filler or tautology. Every sentence earns its place.

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?

With no output schema present, the description compensates by specifying result semantics: no events = no significant moves, provider-limited engines produce nothing, and events exist only when alerts are enabled. It also names the related settings tool, giving the agent enough context to invoke correctly and interpret results.

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 100%, so the schema already documents site_id, limit, and offset. The description adds only the conceptual 'one RankParse website' scope and doesn't repeat parameter syntax. Baseline 3 is appropriate because the schema carries the parameter documentation burden.

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 opens with a specific verb + resource: 'List recent rank-change alert events for one RankParse website,' and enumerates what counts as an alert (top 3/top 10 entries/exits, threshold moves, new/lost rankings). This clearly separates it from sibling tools like get_rank_alert_settings or get_keyword_rank_history by focusing on recorded alert events rather than settings or raw ranking history.

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 explicitly says the tool 'Reads recorded events, never runs a live check,' and that 'a keyword with no events simply had no significant moves,' giving the caller a concrete interpretation of an empty result. It also routes to related setup via 'see get_rank_alert_settings' and explains when events exist. It doesn't enumerate all alternative tools explicitly, but the context is strong.

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