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

Annotations already establish read-only, idempotent, and non-destructive behavior. The description adds meaningful context beyond those hints: proposals are 'durable' and votes 'never authorize code or production changes.' This prevents misuse by an agent that might otherwise treat the totals as approvals.

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?

The description is two sentences with the action front-loaded and no filler. The second sentence supplies an important behavioral caution, so both sentences earn their place.

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 simple read-only listing with no output schema, the description names the main result and includes a key behavioral note. It is incomplete, though, because 'before' is undocumented and the output format or pagination behavior is not described.

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 0%, yet the description adds no meaning for either 'limit' or especially 'before.' The schema only supplies types and constraints; the tool description leaves the cursor/pagination semantics entirely unexplained, so the agent cannot correctly use the 'before' parameter.

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 clearly states a specific read action ('Read recent durable proposals') and a distinctive result ('advisory opinion totals'), which separates it from submit/record siblings. It does not explicitly name sibling alternatives, but the resource and output focus are clear enough.

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?

The description implies when to use the tool: when you need recent proposals and their opinion totals. It also adds a caution that votes are signals and not authorization. However, it gives no explicit when-not guidance or alternative routing among the list/get siblings.

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