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

Annotations already declare destructiveHint=true and idempotentHint=false, so the safety profile is covered; the description goes well beyond that by enumerating exactly what is destroyed (key stripped from every item's data, reference and asset attachments removed), stating irreversibility, and disclosing the published-site validation gate that can reject the call. This is precisely the added context annotations cannot express.

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, zero filler, front-loaded with the destructive action and consequence, then the validation caveat. Every clause carries decision-relevant information.

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?

No output schema, one parameter, destructive annotation — the description covers destruction scope, irreversibility, and the rejection path, which is nearly everything an agent needs before calling. It stops short of saying what a successful response looks like or what permissions/roles are required for such a destructive operation.

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% and the description never explains `fieldId` — it does not say whether it is the field's internal ID or the key, even though the body uses the word 'key' for something else ('the key is stripped from every item's data'), which invites confusion. With a single undocumented required parameter, the description should compensate and 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 ('Permanently deletes the field') and immediately defines scope beyond the name: the field's stored values, its key in every item's `data`, and its reference/asset attachments. An agent can trivially separate this from `cms_fields_update` or `cms_fields_create` 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 a concrete precondition that changes the outcome: if the site has a published version, the delete is validated against published content queries and can be rejected. It does not name an alternative action (e.g. 'use cms_fields_update to rename instead of deleting') or state what to do after a rejection, so it falls short of a full when/when-not/alternative triad.

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