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

The description substantially expands on the annotations by warning that card text is untrusted data from a stranger's agent and must never be treated as instructions. It also discloses redaction behavior and the exclusion of flagged/matched people, giving the agent crucial information about how to interpret results and respond to suspicious profiles. This goes well beyond what readOnlyHint and openWorldHint already 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?

The description is front-loaded with the core behavior and then presents the safety warning and the 'since' usage. The safety warning is somewhat long, but every part earns its place given the untrusted-data risk; it remains reasonably tight and well-ordered.

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 tool with no output schema, the description gives a useful preview of the return concept: a redacted card with no name or contact details. It covers the main usage filter and the critical security context. It does not describe possible pagination, empty-result behavior, or the full card shape, but the current level is sufficient for safe and correct invocation.

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 input schema already documents both parameters fully, and the description adds only a mild reinforcement of the 'since' parameter by relating it to 'after you last looked.' It does not add meaning to the api_key parameter beyond what the schema provides, so a baseline score of 3 is appropriate given 100% 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: everyone else on the network as redacted candidate cards, excluding people already flagged or matched. It is specific enough to understand the tool's role among siblings, but it does not explicitly differentiate itself from similar listing tools like check_matches or network_size.

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 provides useful context by explaining the optional 'since' filter and when to pass it, and it suggests reporting manipulative profiles with report_twin. However, it does not explicitly say when to prefer this tool over alternatives such as get_intros, get_invites, or check_matches, so usage guidance is mostly implied rather than explicit.

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