Add Do Not Contact

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

With no annotations, the description carries the full burden and usefully discloses the downstream effect ('future sends to them are refused'), which is genuine behavioral context. However, it omits idempotency, what happens if the contact already exists, permission requirements, and error behavior for a mutation tool.

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: purpose first, consequence second, with zero filler. Both sentences earn their place and the effect is front-loaded after the core action.

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?

An output schema exists so return values needn't be explained, and the purpose plus effect are covered. But for an unannotated mutation tool the description leaves gaps on idempotency, dedup behavior, and parameter format that an agent would benefit from.

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 0% and the description never explains the single parameter. It says 'someone' but doesn't clarify that the identifier is an email or phone, expected format, or whether both are accepted. The self-descriptive name 'email_or_phone' partly rescues it, but the description adds no meaning.

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: 'Record that someone asked not to be contacted,' and the second sentence clarifies the effect ('future sends... are refused'), which implicitly distinguishes it from the send_* siblings. It stops short of naming siblings explicitly, so it's clear but not sibling-differentiated.

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 trigger ('someone asked not to be contacted') is implied clearly enough to know when to reach for it, but there is no explicit when-not guidance and no sibling is named as an alternative. Adequate but reasonably inferential.

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