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

The description claims the tool ends/deletes a viral alert and can stop paid refresh crawls, which are destructive side effects. The annotations mark destructiveHint as false, directly contradicting the described behavior. Under the scoring rules, this contradiction forces a score of 1.

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 core purpose and side effects are front-loaded and compact. However, the description says 'Free.' and then repeats 'Cost: free.' at the end, so not every sentence earns its 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 one-parameter mutation with no output schema, the description covers the lifecycle, side effects on paid refresh crawls, and the error case. It is nearly complete for an agent to call it correctly, with only a minor gap around the success response shape.

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 single parameter alertId is already fully described in the schema (100% coverage). The description repeats the source of the ID and adds the not_found behavior, but does not add new constraints or format details, so baseline 3 is appropriate.

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 opens with the specific verb 'Ends' and the resource 'viral alert,' and identifies the exact source of the alertId. It is unambiguous and clearly distinct from sibling tools like create_viral_alert and delete_watchlist.

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 tells the agent the alertId comes from list_viral_alerts or create_viral_alert, and explains the side-effect condition for stopping paid refresh crawls plus the not_found error. It lacks an explicit when-not-to-use statement or alternative, but the context is otherwise clear.

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