Draft an AI outreach email

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

With no annotations, the description carries the full burden and does disclose meaningful behavior: the backing endpoint (POST /api/v1/outreach/draft), that a server-side claude-sonnet-4-6 call is involved, and the return shape (subject, body, confidence, reasoning). It omits key side-effect facts — whether the draft is persisted, whether it costs tokens/money per call, and whether repeated calls are safe.

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, front-loaded with purpose before implementation and return details; nothing is redundant. The reference to the internal package path (packages/ai) is minor noise for an agent, keeping it from a 5.

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?

There is no output schema, so covering return values is a real contribution, and the model/endpoint detail adds context. However, for a network mutation-adjacent tool with zero annotations and no output schema, the description leaves open whether the draft is saved and how failures/rate limits are surfaced.

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 100%, so guestId, recentWork, and episodeAngle are already documented in the schema. The description adds no syntax, format, or default information beyond that, so the baseline of 3 applies.

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 + resource (generate an AI outreach email draft) and names the target entity (a guest), which is unambiguous against the guest-CRUD siblings. It does not explicitly contrast itself with any sibling or state scope limits (e.g., one guest at a time), so it falls just short of a 5.

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?

No when-to-use, when-not-to-use, or prerequisite guidance is given. It never says the guest must already exist (only implied by the required guestId) or what to do instead if a draft already exists. The agent must infer all usage context from the name alone.

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