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

Annotations already declare destructiveHint=true, openWorldHint=false and idempotentHint=false, so the description earns credit for adding genuinely new facts: nothing is provisioned immediately and carrier approval takes 8-12 weeks. That latency/human-in-the-loop disclosure is exactly the kind of context annotations cannot express. It does not, however, say what happens after submission (request ID? where to track status?) or address why a non-provisioning request carries destructiveHint=true.

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 tight sentences with the core constraint (nothing provisioned, 8-12 week carrier approval) front-loaded. No filler, no restatement of the tool name.

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?

With no output schema and four required parameters at 25% coverage, the description should say what the call returns and how to check approval status. It covers the single most important behavioral fact (long async approval) but leaves the post-call path and most parameter expectations to inference.

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 only 25% — just use_case has a description — so the description needs to compensate and largely does not. The parenthetical "(or a toll-free number they set up)" loosely maps to the type enum, but business_name and monthly_volume receive no explanation of format or expectation anywhere, and no parameter is mentioned by name.

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?

"Ask our team for a short code (or a toll-free number they set up)" gives a specific verb (request) and resource (short code / toll-free number), and "Provisions nothing by itself" cleanly separates it from provisioning siblings like purchase_number or bulk_purchase_numbers. It stops short of naming any sibling explicitly, so it lands at a clear-but-not-differentiating 4.

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?

The intent (you need a short code or toll-free number and must go through an approval process) is implied but never stated as a when-to-use rule. There is no guidance on when to prefer this over purchase_number/search_available_numbers, nor on how it relates to get_toll_free_verification or list_number_requests for follow-up.

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