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

Goes well beyond the destructiveHint annotation: explicitly states the first call writes nothing, that the second call is the actual mutation, that a 'confirm' boolean is ignored, that the token is single-use and expires in 5 minutes, and that items.delete permission is required. This is exactly the behavioral detail a destructive tool needs.

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?

Permission requirement and action are front-loaded, then the two-step contract follows in short declarative sentences. Every sentence adds a constraint an agent could get wrong; nothing is redundant.

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?

With no output schema, the description compensates by naming the first call's return fields (confirmation_required, summary, confirm_token). What the successful second call returns, and how token expiry surfaces as an error, are not stated.

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 coverage is 0%, so the description carries the burden. It fully explains confirm_token's lifecycle and the 'repeat the same arguments' requirement, and warns that a confirm boolean has no effect. order_id is only implied by 'purchase order' rather than described, which keeps it short of a 5.

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 ('Delete a purchase order') and adds the required permission scope, which an agent needs before calling. It does not distinguish itself from the sibling cancel_purchase_order, so an agent must infer whether deletion or cancellation is appropriate.

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?

Gives a precise procedural contract: first call is a dry-run that returns only confirmation_required/summary/confirm_token, second call with identical arguments performs the write. It does not say when to choose delete over cancel_purchase_order, so alternatives are left implicit.

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