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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds useful behavior beyond that: the result marks which entry a merge would retain, and the no-qid mode is scoped to 'largest clusters still to merge', implying ordering/priority — genuinely useful context.

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 tight sentences, zero filler, with the core purpose front-loaded and the two input modes following. Every clause carries information about behavior or usage.

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?

An output schema exists, so return-value detail is not required, and annotations cover safety. The description explains both invocation modes for a read-only listing tool with 2 params, leaving only minor gaps (no explicit sibling routing) for an otherwise complete definition.

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 only 50% (qid has a pattern but no description), so the description must compensate, and it does: it defines what supplying or omitting `qid` returns. It also contextualizes `limit` via 'largest clusters', adding meaning beyond the schema's bare 'how many clusters'.

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 clearly states what the tool returns: entries sharing a Wikidata QID, annotated with the entry a merge would keep. It is a specific resource (duplicate QID clusters) distinct from action tools like merge_entry or unmerge_entry, though it never names a sibling to disambiguate against get_entries or search_entries.

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 gives explicit conditional usage: pass a `qid` for that item's cluster, omit it for the largest clusters still to merge. This explains both operating modes clearly, but it stops short of naming alternatives or stating when-not to use the tool.

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