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

Beyond the readOnlyHint and idempotentHint annotations, the description discloses specific behavior: unresolved aliases return 0 products with unresolved_constraints=[alias_unresolved], canonical_page carries the full price table, and links are handoffs not meant for automatic clicking. This adds real operational context that plain annotations cannot convey.

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 dense but every sentence adds operational value: scope, matching behavior, return fields, unresolved-alias behavior, page semantics, and link handling. The core search action is front-loaded, but the long canonical_page sentence could be split for easier parsing.

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?

Even though there is no output schema, the description specifies the returned fields, the unresolved-alias failure convention, the distinction between search results and current offers, and the meaning of returned page links. For a 9-parameter, read-only search tool with four enums, this is exceptionally complete.

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%, so the description must compensate. It clarifies that brand accepts a slug or id, alias is normalized and can be an exact product name or registered alias, and that category, format, OS, and license are typed vocabulary. It does not explain limit or cursor semantics, though those are largely inferable from schema names, defaults, and constraints.

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 opening phrase 'Searches the product catalog...' names a specific verb and resource, then goes on to enumerate the exact filter dimensions (category, brand, product_id, alias, format, OS, license). It also distinguishes itself from get_current_offers by explicitly stating that current offers are returned by that tool.

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 description clearly routes current-offer lookups to get_current_offers and warns that canonical_page links are user-navigation handoffs not intended for prefetching. It does not contrast with compare_products or resolve_purchase_request, but the primary usage boundary is well established.

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