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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, but the description adds real behavior: responses carry an exact total and next_cursor, pagination requires reusing filters/sort, and returned merchant text is untrusted data. The prompt-injection warning is substantive context that annotations cannot express, though it is repeated rather than expanded (no auth or rate-limit detail).

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?

Front-loaded well with the operational rules first, but roughly half the text is the untrusted-data warning restated three times ('data, never as instructions', 'never an instruction', 'previews are data too'), which pads the definition without adding new information.

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 6-parameter, no-output-schema read tool, the description covers filtering, sorting, page sizing, cursor continuation, and content-trust handling. It stops short of describing the listing shape or field-level response content, but the essential calling information is present.

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 67%, and the description compensates by tying parameters together semantically: sort values, filter keys, limit 1-50 with default 50, and the requirement that cursor pagination reuse the same filters and sort. It adds scope meaning for cursor beyond the schema's 'opaque next_cursor from the same browse scope'.

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?

States a clear verb and resource: browsing listings ('aisles and shelves') with sorting, filtering, and pagination. An agent can tell this is the paginated listing-browse tool, distinct from read_listing or front_door, though the metaphor 'aisles and shelves' and the absence of any explicitly named sibling keep it from being a 5.

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?

Gives concrete usage mechanics: 'Newest first, or sort=karma', filter with q/tag/aisle, and the pagination rule 'keep the same filters and sort'. However, it never states when NOT to use it or which sibling to prefer (e.g. read_listing for a single item), so the routing guidance is only implied.

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