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

Annotations only supply destructiveHint=true, so the description carries the disclosure burden and does well: terms persist in the DB and reappear on same-slug re-creation, different-slug re-creation leaves terms orphaned and the taxonomy empty, and bound archive templates get unbound and listed in the answer. It stops short of stating irreversibility or permission requirements, but the consequences of the mutation are clear.

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 the core action and consequence, and every sentence adds distinct information (refusal rule, term persistence, rename pitfall, template unbinding). It is dense but slightly long, with the rename discussion spanning several clauses that could be tightened.

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 destructive one-param tool with an output schema already covering the returned unbinding list, the description supplies everything needed: what is refused, what survives, the rename pitfall, and a required pre-read doc. No material gap remains.

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 100% for the single slug param, so baseline is 3; the description earns above baseline by attaching critical semantics to slug values (same slug preserves terms, a changed slug orphans them). That is genuinely additive to the schema's terse 'from list-taxonomies' note.

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 (unregister) and resource (taxonomy) with an explicit scope constraint: only taxonomies Fabrement created, core/plugin ones refused. It is immediately distinguishable from sibling delete-term and update-taxonomy 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?

Explicit when-not (core/plugin taxonomies are refused) and names the correct alternative for a different intent: keep the slug and use update-taxonomy {rewrite}/{singular,plural} to change URL or name. It also routes the agent to get-skill-doc before the first call.

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