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

Goes well beyond the annotations (readOnlyHint=false, destructiveHint=false, openWorldHint=true): it discloses idempotency, that unknown taxonomy values are *silently* coerced to categories, that custom taxonomies are unsupported, the two possible return shapes on 'existed', and that wp_timeout/wp_unreachable leaves write state ambiguous so the agent must verify rather than retry blindly. This is exactly the non-obvious behavior an agent needs.

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-loads the core operation and idempotency in the first clause, then tapers into edge cases and error handling. Dense with parentheticals but every sentence carries operational information; no filler to cut, though the nesting makes it slightly harder to scan.

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 6-parameter mutating tool, the description covers the risky parts (idempotency, silent coercion, ambiguous failure states) rather than duplicating output schema fields. An agent could call this correctly and safely on the first attempt.

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 carries full burden and does most of it: taxonomy default plus coercion rule, parent restricted to categories, workspace meaning and optionality, and name's role in the idempotency check. 'slug' and 'description' are never mentioned, leaving two parameters to convention.

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 ('Eine WordPress-Kategorie oder einen Tag anlegen') and immediately scopes it away from generic term creation with the idempotency note. An agent can distinguish it from wp_list_terms or wp_create_post without opening any 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 clear operational context: idempotent behavior when the name exists, taxonomy fallback for unsupported values, parent only applies to categories, and workspace optional when a single workspace exists. It stops short of naming a concrete alternative tool (e.g. wp_list_terms for pre-checking), so it lacks explicit alternative routing.

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