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

Annotations already signal read-only, open-world, non-destructive; the description adds meaningful behavioral context: bounded truth states, 'never safe/approved/guarantee', price never guessed, provenance source naming, and server-side limitations (no order/payment actions). This goes well beyond the annotations.

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 a single dense paragraph with many clauses; it leads with the main action but packs in caveats (truth states, provenance, safety) that could be structured. It remains informative and not redundant with schema.

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 tool with 6 params, nested objects, and an output schema, the description covers the tool's dual modes, expectations, safety boundaries, and change-detection behavior, leaving little ambiguity. Output schema covers return values.

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 covers 100% of params with descriptions. The tool description adds context on priorEvidence's role (re-check with change detection) and merchant allowlist requirement, but otherwise relies on schema for individual parameter semantics—a solid improvement over the baseline.

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 explicitly states the tool reports one product's current offer or prepares/re-checks normalized checkout evidence, with specific data points (price, availability, provenance, truth states). This clearly distinguishes it from siblings like search_retail_products (searching) and compare_product_offers (comparing).

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 explains two distinct invocation modes (offer vs checkout evidence) and the condition for re-check (passing priorEvidence). It provides context for preflight use and states the server never places orders, but it does not explicitly contrast with sibling tools or state when not to use it.

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