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

With no annotations at all, the description carries the full burden. It does disclose the most important behavioral trait — the output is unsigned, KlickyMart never signs or publishes, and proof tags mark a verified purchase — which is genuine value beyond structured fields. However, it says nothing about validation failure behavior, idempotency, rate limits, or what happens when region/proof data is malformed, which matters for a 35-parameter mutation-adjacent builder.

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 key contract — unsigned template, you sign and publish — is front-loaded, and each following sentence adds a distinct rule (location granularity, proof tags, checkout preset). It is dense but not padded; the heavy parentheticals make a few sentences run long, slightly hurting scanability.

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 complex 35-parameter tool with no annotations and no output schema, the description covers the core behavioral contract but leaves large semantic gaps on parameter meaning and on what the returned template actually contains. It is adequate to start a call correctly, but not complete for invoking the tool reliably across its many optional 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?

Schema description coverage is only 46% across 35 parameters, so the description must compensate, and it only covers a handful: region format, price_seen/shipping/tax for the checkout preset, and proof-tag concepts. Many parameters (fee, agent, steps, walls, blocker, narrative, duration_s, delivery_days, btc_route, rating, strict, the *_shown_before_payment family) get no explanation in either schema or description. It also references proof tags (zap/preimage/cashu/order_hash) that do not appear as named properties in the schema.

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 first sentence names a specific verb (returns/builds) and a precise resource (unsigned Nostr kind 422 'shopping experience' event template), plus the scope constraint that KlickyMart never signs or publishes. It also names the sibling submit_review, so an agent can distinguish this tool from the review-submission path without opening either 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 gives concrete usage context: sign with your own site-specific key and publish to your own relays, optionally POST the signed event to /reviews or the submit_review tool, and location must be ZIP3/US-state/country only. The preset=checkout paragraph adds a clear when-to-call rule ('one call at the payment screen'). It stops short of explicit when-not-to-use guidance or a full comparison with submit_review.

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