set_email_preferences

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It does reveal a key side effect: setting preferences can re-subscribe an opted-out person, which is exactly the kind of behavioral warning an agent needs. It doesn't mention merge-versus-replace semantics or return values, but the most important safety-related behavior is disclosed.

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?

The description is two sentences with no filler. The primary action is front-loaded, and the cautionary note directly follows. Every word contributes to either defining the action or constraining its use.

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 two-parameter tool with no output schema, the description plus schema cover the core requirements: what it does, when to use it, and a critical safety warning. The main missing piece is whether the topics object replaces all preferences or merges with existing ones, which is not specified in either the schema or the description. Still, the tool is simple enough that this is not a severe gap.

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 50%: the topics parameter includes an example and boolean semantics, while email relies on its 'format: email' attribute. The tool description adds 'which topics a person receives,' which maps to the topics parameter but does not exceed what the schema already conveys. Since the schema already explains the nested object well, a baseline score of 3 is appropriate.

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 and resource: 'Set which topics a person receives.' This clearly defines the tool's purpose and naturally distinguishes it from the sibling get_email_preferences, which is the read counterpart. The resource is precise enough that an agent can tell it apart from suppression or broadcast tools.

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 description gives an explicit condition for use: 'Only do this when they have actually asked.' It also communicates a clear when-not by warning against 'silently re-subscribing someone who opted out,' tying the misuse to spam complaints. This is direct, actionable guidance that leaves little room for misinterpretation.

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