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

Annotations declare only destructiveHint=true and idempotentHint=false; the description adds far more: soft-delete semantics, irreversibility ('cannot be undone'), the blocked-deletion precondition, the two-phase confirmation_token preview flow with safe-retry-on-lost-response semantics, and the success return shape. The retry guidance concerns the confirming call, not delete idempotency, so it does not contradict idempotentHint=false.

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 action and scope in the first clause, then layers id sourcing, the replace workflow, the destructive warning, the precondition, and the return value in descending order of importance. Every sentence carries distinct operational information; no filler.

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?

Despite having no output schema, the description states what a successful call returns (deleted proof info) and documents the confirmation-token response behavior. Combined with the precondition and workflow, an agent has everything needed to invoke this destructive tool safely.

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%, so the baseline is 3; the description still adds value by telling the agent where proof_id values originate (list_identities / list_addresses) and by framing confirmation_token as a two-step preview-then-confirm handshake rather than an ordinary input. It does not add format details, but the schema already supplies the UUID type and description.

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 ('Delete (soft-delete) ... regulation proof documents by id') and scopes it to the authenticated customer's uploads. The parenthetical 'soft-delete' immediately distinguishes the operation's nature from a hard delete performed by sibling tools like delete_did or delete_identity.

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?

Explicitly names the sibling tools that supply ids (list_identities / list_addresses) and prescribes the replace workflow: delete first, then call create_regulation_upload_link. It also states a hard precondition (a proof tied to a pending address verification cannot be deleted), which is exactly the kind of when-not guidance that prevents failed calls.

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