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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld), so the bar is lower, yet the description still adds real behavioral context: default 3 / max 5 candidates, the remote disabling of Google and fallback, bounded direct-record admission, and the explicit withholding of public prose, aliases, external links and media. That last point materially sets agent expectations about output completeness.

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?

Purpose is front-loaded and the total length is reasonable, but several fragments are opaque internal jargon ('bounded direct-record admission without recursive content certification', 'identity evidence and uncertainty remain separate') that a caller cannot act on. Those sentences do not clearly earn their 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 and 7 undocumented parameters, the description does some of the needed work by disclosing withheld fields and candidate limits, but it leaves the return shape (how identity evidence vs uncertainty are presented) and the lang parameter unexplained, so an agent is only partially equipped.

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 0%, so the description must carry the burden and it only partially does. It clarifies limit behavior (default 3, max 5, beyond the schema's null default), place/type filtering, and that provider=google and fallback are unusable, but 'lang' is never mentioned and the meaning of 'type' is left implicit.

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 opening clause states a concrete verb and resource: returns Wikidata entity candidates by name, with place/type filtering. That is enough to know what the tool does, but it never differentiates itself from the many siblings (kg_lookup_entities, kg_resolve, kg_discover_identity), so an agent cannot tell which search-like sibling to pick from the description alone.

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?

There is no when-to-use guidance and no routing to alternatives. The only usage-relevant note is 'Google and fallback are disabled remotely', which usefully warns that provider=google and fallback=true will not work, but that is a constraint, not guidance on when to choose this tool over the other kg_* tools.

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