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

Goes well beyond the annotations by disclosing consequences: the order can no longer be disputed, the acceptance is cryptographically anchored, and it requires the caller's key ('Needs your key'). The annotations only mark it as a non-read-only, non-destructive, non-idempotent write; the description supplies the irreversibility and auth context.

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?

Effect-first ordering with the fallback deadline and key requirement packed into two sentences; no filler. The quoted buyer line is slightly ornate but serves as a fast framing cue.

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 one-parameter mutation with no output schema, it covers effect, irreversibility, side effects (Word Pass), and auth. It does not say what the caller gets back or what happens on a repeat call, a minor gap given idempotentHint=false.

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?

Single parameter with 100% schema coverage, and the schema already explains 'or_…' format and that the id comes from buy or my_orders. The description adds nothing further about order_id, so the baseline 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?

Names a specific action (accept the delivery) and describes the concrete effect: the acceptance is signed and anchored in Bitcoin and Stellar, counts toward the seller's Word Pass, and locks out disputes. That clearly separates it from siblings like open_dispute, get_order, or recall.

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 buyer framing plus the note that without it a delivery auto-accepts after 14 days gives a real condition for using it versus waiting. There is no explicit 'do not use when' or a named alternative tool, which keeps it short of a 5.

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