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

With no annotations, the description carries the full burden, but it does contribute real behavioral context: anonymous callers receive only the last 5 summaries while a subscriber for that origin gets full history, and results are newest-first. It still omits what a "summary" contains, rate limits, and what happens for non-subscribers at higher limits.

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 front-loaded, zero-waste sentences, but the compression has crossed into telegraphic ambiguity — "drift" and "summaries" are never grounded. Efficient in form, under-specified in substance.

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?

The required `domain` parameter is never mentioned in the description, and with no annotations and no output schema the description should at least indicate the return shape (what a "summary" or a change entry looks like) or that this is a read-only history lookup. Substantial gaps remain for a purpose this thin.

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 both the domain normalization rules and the limit behavior (fake cap 5 for anonymous, subscriber default 20 / max 50, non-numeric ignored) are already fully documented in the schema. The description's tiering note reinforces the limit semantics but adds no syntax beyond it, making the baseline 3 appropriate.

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?

"Newest-first drift" gestures at listing change history but never states what resource the changes belong to (DNS records? host config?) or that the input is a hostname. With 11 siblings in the same host/DNS family, an agent cannot confidently distinguish this tool from lookup_host or endpoint_health based on this text.

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 distinguishes anonymous vs subscriber *results* but gives no guidance on when to call this tool versus siblings like lookup_host or participation_check, and names no alternatives or preconditions. Usage is left entirely to inference.

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