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

Annotations only cover read-only and open-world; the description adds the important traits: unknown taxonomies are silently coerced to categories, page size caps at 100, no total count is returned, success does not prove a valid application password (public endpoint), and the two distinct error shapes with retry advice. Missing only output format/paging mechanics, which the output schema likely covers.

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?

Front-loaded with purpose, then taxonomy behavior, then return/error semantics, then the workspace note. Dense but every clause (fallback behavior, error codes, auth caveat) adds information an agent would otherwise have to guess.

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?

Covers the non-obvious complexity of this tool well: taxonomy coercion, pagination cap, auth caveat, and error recovery, with return fields covered by the output schema. The incomplete coverage of the page and search parameters is the only meaningful gap.

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 0%, so the description must carry the load; it documents taxonomy (default plus silent fallback) and workspace (optional for single-workspace clients) and hints at per_page via the 100-per-page cap. The page and search parameters are never mentioned, leaving two of five parameters unexplained anywhere.

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 ('WordPress-Kategorien oder Tags auflisten') and immediately bounds scope: only categories or tags, custom taxonomies unsupported. An agent can distinguish this from wp_list_posts or wp_create_term without opening the 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 useful context (default taxonomy, silent mapping of other values, IDs feed wp_create_post) and a retry instruction for timeouts, but never names an alternative tool or states the condition under which listing terms is the right choice versus other WordPress listing tools. Usage is implied rather than routed.

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