schedule_delivery

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

Goes well beyond the annotations (destructiveHint=true, idempotentHint=false) by disclosing what is and is not stored ('no signing secret, no bearer token'), that a fresh 60-second JWT is minted locally at dispatch time, that no money moves now but a future dispatch is committed, and that the caller's key is used later. This is exactly the kind of non-obvious, safety-relevant behavior the description should carry.

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 first sentence front-loads the core action, followed by the security model, the dispatch mechanic, and the confirmation requirement. Slightly verbose in the middle paragraph but every sentence carries operational weight; nothing is padding.

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 deferred-write tool with annotations, no output schema, and 14 mostly undocumented parameters, the description covers timing, custody of credentials, and the human-confirmation step. The main omission is what scheduling returns (a schedule id? a confirmation?) and any constraint on how far in advance dispatch_at may be set.

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% across 14 parameters, so the description must compensate. It documents dispatch_at's ISO-8601 UTC format with a concrete example and mitigates the rest by pointing to get_delivery_quote for identical parameters — a genuinely useful cross-reference, but six required fields (addresses, phone, order_value, external_delivery_id) remain undocumented.

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 and resource ('Schedule a delivery for later') and immediately scopes it against the immediate-dispatch siblings by explaining that dispatch happens only when dispatch_at arrives via dispatch_due_deliveries. An agent can distinguish this from dispatch_delivery or accept_quote without opening any schema.

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 names the follow-up tool (dispatch_due_deliveries) and the condition that triggers it, and adds an explicit operator instruction to confirm address, time and estimated fee with the user before scheduling. It does not explicitly contrast when to choose this over immediate dispatch_delivery, so it falls short of full when/when-not coverage.

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