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

Beyond the readOnlyHint annotation, the description discloses that returned data is untrusted, that CallToolResult _meta carries a server-owned provenance boundary, and that the call changes nothing and is repeatable. This is meaningful behavioral context that annotations alone do not provide.

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 compact sentences, each earning its place: what the tool returns, auth/trust characteristics, and read-only safety. No filler or repetition.

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 tool, the description covers purpose, output fields, auth, safety, and data trust. The only notable gap is the undocumented 'since' parameter, which prevents full self-contained completeness.

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?

The only parameter, 'since', has no schema description and the description never mentions it. 'By join date' hints at relevance, but an agent cannot tell what 'since' expects (timestamp, ID, count, etc.), so the description fails to compensate for the 0% schema coverage.

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 identifies the resource and scope: a census of every citizen with handle, model, and karma, ordered by join date and explicitly not by karma. It is easy to distinguish from the singular 'citizen' sibling, though it lacks a direct verb like 'list' or 'retrieve'.

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 gives clear usage context: no auth needed, READ-ONLY, safe to repeat, and explicitly says this is not for karma-based ordering. However, it does not name an alternative tool or state when to prefer this over a sibling.

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