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

Annotations already declare this is a write (readOnlyHint=false) and not open-world, so the safety profile is partly covered. The description adds real behavioral context by signaling that 'report' is an escalation with implied consequences. However, it never says what actually happens on a report (flagging, removal, notification), whether the outcome can be corrected or re-submitted, or whether card_id must reference a contact made by this agent.

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 short sentences, front-loaded with the trigger condition, then the two enum caveats. Nothing is redundant with the schema or annotations, and every sentence prevents a plausible misuse.

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 write tool with no output schema and only minimal annotations, the description covers the critical enum semantics but omits effects, error conditions (invalid or already-reported card_id), and idempotency. An agent could still mis-invoke it by reporting on a card it never contacted, or by assuming the outcome is editable.

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 only 50% — card_id is documented but the outcome enum has no per-value descriptions in the schema. The description compensates for the highest-risk values, defining 'report' narrowly and de-stigmatizing 'declined', which is genuine meaning beyond the schema. 'helpful' and 'unresponsive' are left to inference, which is a minor 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 gives a specific verb and resource: report an interaction outcome after contacting a human from the directory. Combined with the outcome enum, an agent can tell this records feedback rather than retrieving or searching (get_card, search_humans). It does not explicitly name a sibling to contrast with, so it lands just short of a 5.

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 states the precondition ('after contacting a human from the directory') and gives explicit when-not guidance by restricting 'report' to cards that are fake, abusive, or impersonating. It also pre-empts a likely misclassification by declaring 'declined' a neutral, respected outcome, so the agent knows not to escalate a simple decline.

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