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

With no annotations, the description must carry the full behavioral burden. It usefully discloses the retrieve-or-provision semantics and the resulting side effect of creating a number, but says nothing about limits, costs/billing implications, or what the response contains.

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 short sentences with zero waste: what it does, the idempotency rule, then the use case. Front-loaded and appropriately sized for the operation's complexity.

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 an unannotated tool that can create a billable resource, the description is thin on behavioral consequences (cost, number limits, response shape) and has no output schema to lean on. The core semantics are covered, but an agent could still be surprised by provisioning side effects.

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, but the description earns a bump by explaining the default 'return existing number' behavior that force_new overrides. It still ignores area_code and label.

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 ('Get a phone number') and adds the key semantic that it is retrieve-or-provision, which separates it from list_phone_numbers and release_phone_number. It doesn't name those siblings explicitly, so it falls short of full differentiation.

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 it when a website or service asks for a phone number' gives a concrete trigger condition an agent can match against. It offers no exclusions or pointer to alternatives (e.g. listing existing numbers), so it is clear context without routing.

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