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

Annotations already declare destructiveHint=true, but the description goes well beyond them: it says all entries are destroyed with the list, that the action cannot be undone, that failures name the blocking trunks, and that a lost confirm response is safe to retry with the same token. This is exactly the extra behavioral context annotations cannot convey.

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?

Four tight sentences, front-loaded with what is deleted and its destructive nature, then the precondition, then the recovery path. No sentence is filler; each adds an operational fact.

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 exists, and the description compensates by stating the return value ('a confirmation message on success') plus the two-phase preview/confirm protocol. Combined with the annotations and full schema coverage, nothing an agent needs 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% and both parameters are fully documented in the schema, including the confirmation_token protocol and the provenance of 'id'. The description adds no syntax or format detail beyond that, so the baseline 3 applies.

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 precise verb+resource ('Delete ... Voice IN Number Lists') and disambiguates the resource itself as 'caller-ID filters for inbound calls', which separates it cleanly from the sibling delete_trunk / delete_sms_trunk / delete_did tools.

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 states the blocking condition (a list still attached to Voice IN Trunks cannot be deleted), names the fix and the exact alternative tools (update_sip_trunk / update_pstn_trunk with src_number_list_id set to null), and describes the required two-call confirmation flow. An agent has everything needed to decide and proceed.

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