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

No annotations are provided, so the description carries the burden, and it delivers: match semantics, result ordering (best-match first, then fame), the fields returned per hit, and the no-result fallback. It omits any note on pagination beyond limit or rate/cost behavior, which keeps it short of a 5.

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?

Four sentences, front-loaded with the scope and matching rule, then filters, then result shape, then failure handling. Every sentence contributes something distinct; nothing is filler.

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 no annotations, the description still covers what an agent needs: what is searched, how matching works, how results are ordered, what each result contains, and what to do when empty. Nothing essential for correct invocation is missing.

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 the schema already documents query, country, category and limit. The description mostly restates those (country name or ISO, category filter) and adds little parameter-level detail beyond the substring-matching note. Baseline 3 applies.

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 (search) and resource (the atlas's 9,040 castles/fortresses/palaces/ruins) plus the matching semantics (accent- and case-insensitive substring). This clearly separates it from geo-based castles_near and id-based get_castle without opening a 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?

Explains optional narrowing by country and category and gives a concrete recovery path when nothing matches ('retry with a shorter fragment'). It does not explicitly name when to prefer castles_near or top_castles instead, so the routing vs siblings is left partly implicit.

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