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

Annotations already declare readOnly, idempotent, and non-destructive behavior, so the safety profile is covered. The description adds a real trait beyond them — that responses can be very large and should be paged in with a small limit — which directly affects how the agent calls it.

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?

Front-loaded with what is returned, followed by the size warning and a docs link. Two sentences plus a URL, no filler, though the trailing link is the only mildly non-essential element.

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 an output schema present, return values need not be explained, and annotations carry the safety semantics. The description covers purpose, data volume, and a docs reference, leaving only minor gaps such as pagination/ordering of the history.

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%, so the baseline is 3, but the description adds practical guidance absent from the schema: an explicit recommended starting value of 3-4 for limit rather than just the documented default 10 / max 100. monitor_id meaning is left to the schema.

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?

Specific verb+resource: returns the DNS records Oh Dear last saw for a monitor plus the history of changes. It also states the concrete outcome ('spot when a record changed'), which no sibling tool covers, so the agent can distinguish it from the other get_* tools.

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 clear usage intent ('so you can spot when a record changed') and an operational caution to start with limit 3 or 4 because the payload can be large. It does not name exclusions or an alternative sibling, but none of the listed siblings overlaps in behavior.

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