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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered. The description adds the useful precondition about an agent needing a number to call, but says nothing about how many numbers are returned or what an empty result means. A 3 fits given annotations carry most of the burden.

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 action first and the prerequisite second. Every clause adds information; nothing is redundant with the title or annotations.

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 a simple read tool with full annotation coverage and no output schema, the description plus schema is nearly sufficient. The only gap is what the response looks like — whether it is a single number string or a list — which an agent would want to know before branching on the result.

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 50%: the mode parameter is fully documented in the schema, while agentId has no description. The description's phrasing 'assigned to an agent' makes agentId's meaning inferable, but it never addresses how compact vs full affects the returned number data.

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 — retrieve phone number(s) assigned to an agent — with the scope qualifier 'for voice calls'. It is easily distinguishable from neighboring read tools like get_agent_channels or get_voice.

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?

Gives an explicit precondition: check this before start_outbound_call, with the rationale that an agent without a number cannot call. That names the dependent sibling and the condition that selects it, though it does not state any when-not-to-use case.

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