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

Annotations already declare readOnlyHint/openWorldHint/destructiveHint, so the safety profile is covered by structured data. The description adds real behavioural substance beyond that: shelf-bottle hits carry owner username and display name, results are 'ranked like the app', and paging is exposed via nextCursor/hasMore/total. It stops short of noting visibility restrictions (e.g. private shelves) or rate limits.

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?

Two tight sentences with no filler; the result composition is front-loaded and the pagination contract is packed into a short trailing clause. Slightly dense with the colon-and-parenthetical construction, but nothing is wasted.

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?

With no output schema, the description correctly compensates by describing return contents (owner username/display name, nextCursor/hasMore/total). But for a 4-parameter search tool at 25% schema coverage, the meaning of query, limit and offset is still unresolved, and no visibility or ordering guarantees are given.

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 25% — only the cursor parameter is documented in the schema. The description partially compensates by naming the paging contract (nextCursor/hasMore/total), but says nothing about query matching semantics or the roles of limit and offset, which remain undocumented in both places.

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 has a specific verb+resource ('Search bottles') and characterises the result set precisely: other collectors' shelf bottles (with owner username and display name) plus public catalog bottles. This implicitly distinguishes it from the catalog-only sibling search_catalog, but never names that sibling explicitly, so differentiation is left partly to inference.

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?

'Like the app's Search tab' gives a rough mental model of when to reach for it, and the two result classes suggest it is the aggregating search. However, there is no explicit guidance on when to prefer search_catalog, lookup_bottle, or explore_catalog, and no stated prerequisites or exclusions. Usage is implied rather than directed.

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