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

Annotations already declare readOnly, idempotent, closed-world behaviour, so the safety profile is covered. The description adds substantive data-provenance context beyond that: owner-declared or site-published addresses are preferred, domain/hosting inference is a labeled fallback, publisher and hosting countries are separate fields, and none of them independently verifies headquarters. That is exactly the caveat an agent needs to interpret the counts, though it does not discuss ranking, ordering, or how the unknown bucket is computed.

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 sentences, front-loaded with what is returned before the integration guidance, and no filler. The provenance sentence is dense but each clause carries distinct meaning; slightly heavier than a pure list tool needs.

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, the description needn't explain the return structure, and it instead covers the interpretive caveats (inference fallback, publisher vs hosting separation, no HQ verification) that the schema cannot convey. Complete enough to call and interpret correctly; only ordering/completeness of the counts is left implicit.

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 tool takes zero parameters, so the baseline is 4 and nothing in the description is needed to explain input. The description does usefully explain the shape of the produced values (country codes plus unknown) and how they are consumed as arguments elsewhere, which adds a little value on top of that baseline.

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?

States a specific verb and resource ('List country codes and names') plus the exact content of the result (valid listed-site counts and an unknown count), which distinguishes it from siblings like list_categories and list_domains that enumerate other dimensions. An agent can tell what it gets without opening the output schema.

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 concrete downstream usage: feed 'country=FR' or 'country=unknown' into resolve, search_llms_registry, list_domains, list_sections and explore_sections, which is real routing guidance. It stops short of stating when NOT to call it or what to do if the country of interest is absent, so it is clear context rather than a full when/when-not rule set.

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