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

Annotations already cover safety (readOnlyHint=true, destructiveHint=false, openWorldHint=false), so the bar is lower. The description nonetheless adds two useful facts beyond them: results are paginated ('Returns a page of rows') and row_id is the key required by the sibling mutation tools.

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 sentences with zero waste. The trigger condition is front-loaded and the row_id contract is a tight, high-value second sentence.

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?

An output schema exists, so return formatting need not be explained. The description covers the trigger, the shape of results, and the downstream key contract; only the list-site-data relationship and the untaken param descriptions are missing.

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 60%, so the schema already documents table, search, and page_size. The description mentions pagination but does not clarify 'page' or 'site_id' (undocumented in the schema) or the page_size default of 20, so it does not compensate for the remaining gap.

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 names a specific reader action ('see records in one of their WebTwizz site's database tables') and gives concrete examples (bookings, orders, products). It does not, however, distinguish itself from the sibling list-site-data, leaving a real ambiguity about get-vs-list semantics unaddressed.

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?

It explicitly states the trigger condition ('when the user wants to see records') and links forward to update-site-data and delete-site-data as consumers of the returned row_id. No when-not guidance or direct comparison to list-site-data is offered.

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