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

destructiveHint=true is already in annotations, but the description goes well beyond it: posts are orphaned rather than deleted (and recoverable only under the SAME slug), the archive page and fields file are deleted while field values persist, calling on an already-gone slug cleans up a leftover fields file, the archive template binding is dropped, and render bundles are surfaced via renderFiles with a warning that one bundle may serve several types. This is rich, non-obvious operational detail.

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?

Dense and somewhat parenthetical, but nearly every sentence carries a distinct constraint (orphaning, refusal, force, renderFiles, slug-stability). Front-loaded with the core delete action, though the parenthetical asides make it harder to scan than it could be.

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, irreversible-feeling operation, the description covers consequences, refusal paths, recovery conditions, collateral artifacts (archive page, fields file, template binding, render bundles), and even lightly previews the response ('the answer names what was left in place'). An output schema exists, so return values need not be detailed, and nothing an agent needs to call this safely 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 baseline is 3. The description reinforces force's semantics ('pass force:true if that is meant') and the slug's origin, but adds essentially no syntax or format detail beyond what the schema already states for both parameters.

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 ('Unregister a custom post type Fabrement created and drop its definition') and explicitly distinguishes itself from siblings: it is 'NOT a way to rename one' and points to update-post-type for that. An agent can pick it apart from create-post-type, update-post-type, and the other delete-* tools 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?

Extensive routing: when to use (existing Fabrement slug), when not to (renaming → update-post-type with {rewrite}/{singular,plural}), refusal conditions (core/plugin types, posts still existing), the force:true escape hatch, and a pre-flight instruction to read the skill doc and confirm with the user. This is the strongest category for this definition.

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