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

Beyond the destructiveHint annotation it discloses irreversibility ('Não tem volta'), a safety guard requiring confirm_name to match the current name, that the search index is removed along with the document, and that target_user_id is admin-only and defaults to the authenticated account. These are exactly the traits an agent needs before invoking an irreversible write.

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 action and scope, then the irreversible warning, then the guard, then the alternative workflow — a sensible priority order. It is dense and slightly run-on, but every sentence carries actionable content.

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, no-output-schema tool it covers the essentials: what is destroyed, the verification mechanism, the account-targeting rule and the replacement alternative. It stops short of saying what a failed confirmation or a successful deletion returns, which an agent handling errors would want.

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% and the description largely restates it (confirm_name must match, target_user_id admin-only, default account), adding little new syntax or format detail. The pointer to list_kb_documents for obtaining the name is the only marginal addition over the schema.

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?

Opens with a specific verb and resource ('Apaga um documento da base de conhecimento') and enumerates the covered media types, so an agent can separate it from delete_email_template, delete_quick_reply and other delete siblings without opening a schema. It also states the secondary effect (search index removal), which sharpens what the tool actually does.

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 concrete routing: for replacing an image, use create_kb_image then delete the old one, and for the exact name use list_kb_documents. It does not name a sibling to prefer when the goal is merely editing metadata (update_kb_document), so the 'when not to delete' case is only implied.

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