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

Annotations only indicate readOnlyHint=false, idempotentHint=false, etc., which convey that this is a mutating, non-idempotent operation. The description goes far beyond this by disclosing stock reservation, price/VAT/shipping snapshot, delegation policy consultation, the 15-minute expiry, and the combined postage behavior. This gives the agent a strong mental model of side effects and timing.

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 dense sentences with no filler. The core action is front-loaded, followed by key behaviors, and then a specifically actionable warning about postage. Every sentence earns its place and supports correct invocation.

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 tool with no output schema, the description conveys the essential return value (an intent id) and the critical expiry timing. It also warns about the sequencing constraint with confirmation. The only minor gap is that it does not describe the exact response structure beyond the intent id, but this is acceptable given the complexity and actionable guidance provided.

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?

The input schema has 100% parameter description coverage, so the baseline is 3. The description does not add explicit per-parameter details beyond the schema, though it does give useful context about how address_id relates to combined postage. Since the schema already documents product_id, quantity, address_id, and payment_method_id well, no additional parameter explanation is necessary.

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: 'Create a purchase intent for a product.' It then differentiates itself from the sibling confirm/cancel tools by describing the creation lifecycle, including stock reservation, price snapshot, and expiry. An agent can clearly distinguish this from purchase_confirm_intent and purchase_cancel_intent.

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 concrete usage context: intents expire after 15 minutes, and combined postage only applies when earlier orders are unshipped, with an explicit recommendation to confirm each purchase before creating the next intent. This effectively tells the agent when to create an intent and warns about the full-postage pitfall. It does not explicitly name purchase_confirm_intent as the alternative, but the guidance is clear enough.

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