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

Beyond the readOnly/non-destructive annotations, it discloses non-obvious behavior: rows are compact, a filtered page can be empty yet still carry a nextCursor, and OAuth is required. The empty-page-with-cursor warning is exactly the kind of trait an agent could not infer from structured fields and would otherwise misread as end-of-results.

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 with the use case and pagination rule, which are the highest-value facts. A few sentences restate guidance already present in the parameter descriptions (search_cultivars then filter by cultivarReferenceId appears in both), which is mild redundancy but not harmful.

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 13-parameter read tool with an output schema, the description covers authentication, pagination, and the search-vs-detail split well. Minor omissions remain: default/max page size behavior and any result ordering are left entirely to the schema.

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 already 92%, so the baseline is 3; the description adds a useful nuance by separating 'q or title' for unlinked/legacy listing titles versus cultivarReferenceId for indexed cultivar matching. It stops short of explaining limit or the price range interplay, so it modestly exceeds the baseline rather than fully replacing the schema.

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?

Opens with a specific verb and resource ('search, filter, or page through their own listings') and immediately scopes it to the signed-in user, which separates it from list_public_listings and search_public_listings. It also names get_listing as the detail counterpart, so the agent can distinguish it from siblings without opening any schema.

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?

Explicitly states the triggering condition ('when the signed-in user asks to search, filter, or page through their own listings') and routes to alternatives: get_listing for private notes/images/full detail, and search_cultivars first when cultivar data is needed. It also spells out the pagination protocol (follow nextCursor until null, keep the same filters).

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