add_contact

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

With no annotations, the description carries the behavioral disclosure burden and does so well: it explains idempotency ('Safe to retry'), the one-contact-per-workspace rule, and that re-adding an existing email joins the audience rather than duplicating the contact. It does not cover permissions or errors, but the key behavioral edge cases are 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 three sentences with no filler. It front-loads the core action, then adds high-value behavioral context, and ends with the retry guarantee. Every sentence earns its place.

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 tool with no output schema and no annotations, the description covers the most important contextual details: idempotency, uniqueness across workspaces, and audience membership semantics. It is not exhaustive about response values or failure modes, but it is complete enough for correct invocation in most cases.

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%, so the description must compensate for parameter meanings. It refers to 'someone' and 'address,' which loosely maps to email, and 'audience' maps to audience_id, but it does not explain optional first_name/last_name, the role of email as the lookup key, or parameter relationships. The description adds little beyond the schema's field names.

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 clearly states the verb 'Add' and the resource 'someone to an audience,' which distinguishes it from siblings like add_suppression (adding to a suppression list) and remove_from_audience (removing membership). The addition of uniqueness semantics further clarifies exactly what the tool does.

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 implies usage when adding a contact to an audience and explains the behavior for existing contacts, but it does not explicitly state when to prefer this tool over alternatives or when not to use it. No sibling comparisons or exclusions are provided, leaving the agent to infer routing from the tool name and purpose.

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