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

With no annotations supplied, the description carries the full behavioral burden and does state two genuinely useful traits: it is read-only and requires no API key. It also signals that the full normalized field set is returned and that the tool spans both goods and flight fares. It omits what happens on a missing or invalid goods_id, which is the main remaining behavioral gap.

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?

Three short sentences with the action front-loaded and each clause adding new information (scope, field completeness, cross-domain IDs, auth requirement, read-only). 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?

For a one-parameter read tool with no output schema and no annotations, the description covers the essentials: what it fetches, the key, the output richness, and the auth requirement. Only the not-found/error behavior and the meaning of "LOCAL" are left unresolved.

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 must supply the meaning for goods_id, and it does add real value by revealing that the identifier namespace spans both goods and flight fares — a polymorphism an agent could not guess from {"type":"string"}. It still gives no format, example, or prefix convention for the ID.

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?

"Get one LOCAL shelf item by goods_id" gives a specific verb (get one), a specific resource (shelf item), and the lookup key, and the word "one" implicitly separates it from the sibling shelf_search. The parenthetical clarifies that it covers both goods and flight fares, but the meaning of "LOCAL" is never explained, so an agent can't fully anchor the resource.

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?

Usage is implied rather than stated: retrieve a single item when you already have its goods_id, and it works even without an API key. No sibling is named as the alternative (e.g., shelf_search for browsing, product_detail for catalog data), so the agent must infer when this beats a search call.

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