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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description adds real behavioral value beyond them: the return shape ('array of fictional (AAA) 555-01XX numbers'), the guarantee that these are fictional-only, and the city/state coupling rule.

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?

Three compact sentences: purpose first, then usage/constraint, then return contract. No filler, and the most important routing information is front-loaded.

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, the description compensates by stating the return format and the fictional-number guarantee. Combined with full schema coverage and annotations covering safety, an agent has everything needed to call it correctly.

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 baseline is 3, but the description adds meaning beyond the schema by explaining that 'city selects a local area-code pool' and must match state — the schema only says 'must match state if given' without describing the area-code mechanism.

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?

The description opens with a specific verb+resource ('Generate fictional US-format phone numbers') and scopes it to a fictional 555-01XX range, which cleanly separates it from siblings like generate-ssn or generate-card-number. The 'no subscriber lookup' clause further disambiguates it from any real lookup tool.

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?

'Use for US demo phone fields' gives a clear intended context, and the city/state matching rule signals a precondition. However, it names no alternative tool and states no explicit when-not condition, so it stops short of a full routing instruction.

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