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

Annotations already establish readOnlyHint=true and openWorldHint=false, and the description adds genuine behavior beyond them: results are paginated, the caller must follow next_offset to continue, and keyword filtering can narrow the set. It does not disclose rate limits, auth needs, or what the payload of each page looks like, but for a read-only list tool the pagination contract is the critical piece and it is stated.

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 sentences: the first front-loads the trigger conditions, the second the capability and paging directive. Nothing is padded, though the bilingual split means the agent must read both halves to assemble the full picture rather than getting one coherent statement.

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?

For a 5-parameter, no-output-schema tool, the essentials of browse-and-paginate are present, and the read-only annotations remove the need to discuss side effects. However, the exact pagination mechanics (offset vs next_offset relationship) and the meaning of limit/lang are left implicit, so an agent may still guess on the first call.

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 only 20% — just the query parameter is documented. The description covers the keyword filter and hints that next_offset is the paging cursor, but it says nothing about lang, limit, offset, or how to choose among the 14 kind enum values. With low coverage the description needed to compensate for those parameters and largely does not.

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 ('Page through a dataset') and backs it with concrete scale examples (454 equipment, 979 abilities, 596 enemies), which tells an agent this is a bulk browse/list operation rather than a single-record fetch. The only blemish is that the examples ('abilities') don't all map cleanly onto the kind enum ('skills'), so an agent can't infer the enum from prose 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?

The opening clause gives explicit trigger conditions: call when the user wants a list of some data class, statistics, or an export. It also says 'optionally filtered by keyword', implying filtering is optional. It stops short of naming when to prefer a sibling such as search_ffrs or get_entity, so routing between browse-vs-search is left to inference.

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