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

Beyond the annotations (readOnlyHint=false, openWorldHint=true), the description discloses storage privacy, the signed 24-hour link, the delivery.sent event, the one-delivery-per-purchase rule, and the untrusted nature of the note. These details give the agent a complete mental model of side effects and constraints, exceeding what annotations alone provide.

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 dense but every sentence earns its place. It opens with the core action, then flows logically through modes, note, events, constraints, error cases, and reply format. There is no fluff or repetition, and the most critical information is front-loaded.

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 mutation tool with 7 parameters and multiple error paths, this description covers all necessary aspects: prerequisites, input options, size limits, error conditions, reply structure, and side effects. Nothing an agent needs to correctly invoke it is missing. The absence of an output schema is compensated by a clear description of the reply fields.

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?

Although the schema already documents most parameters (86% coverage), the description adds crucial semantics: the exact exclusivity between content_base64 and url, the 4 MB decoded size limit, the filename pattern implication, content_type default, and the idempotency_key behavior (including secret replay refusal). This adds meaning well beyond the schema descriptions.

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 begins with a specific verb and resource: 'Attach the deliverable to a purchase you sold'. It clearly distinguishes this from sibling tools like getDelivery (which reads deliveries) and recordPurchase (which records a purchase). The scope is unambiguous.

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?

It explicitly states prerequisites ('needs your API key; only the seller of the purchase may'), explains the two mutually exclusive delivery modes (content_base64 vs url), and enumerates error conditions (conflict, forbidden, not_yet) with their triggers. It also mentions the buyer reads via getDelivery, providing context for when this tool is the right choice.

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