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

The annotations already declare this a safe, idempotent read. The description adds behavior the annotations cannot: the row-level payload (rhythm, answer status, latest-answer pointer) and the expectation that the list may be sparse or populated depending on site maturity. It does not cover ordering, size limits, or pagination.

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 sentences, front-loaded with the resource definition, then the follow-up action, then the differentiating note. Each sentence carries information, though the 'questions members asked Anry to keep answering' phrasing is slightly conversational and the middle get_report sentence could be tighter.

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 usefully describes what a row contains and how to follow up via get_report, which is what an agent needs to act on results. It stops short of return-volume expectations or pagination behavior, a minor gap for a single-parameter read tool.

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?

There is a single parameter with 100% schema coverage, and the schema already documents site_id as a UUID sourced from list_sites. The description adds no further meaning about the identifier beyond that, which is the expected baseline when the schema does the work.

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 resource (the site's question watchlist) and defines it precisely as questions members asked Anry to keep answering, plus the per-row content (rhythm, answer status, pointer to latest answer). It also distinguishes the tool from the sibling list_opportunities by explaining that this list fills first on a young site.

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 routes the agent forward explicitly: 'Call get_report with a row's report_id for the answer document,' and contrasts the tool's timing against list_opportunities. There is no explicit negative case (when not to call it) and no stated prerequisite beyond the site_id parameter, so it falls short of a full when/when-not formulation.

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