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

Annotations already declare destructiveHint=true and idempotentHint=true, so the safety profile is known. The description does add real value by disclosing the preview-by-default gate and the retention of visit data, but it omits other destructive consequences a caller would want, such as whether associated goals/alerts are removed and what happens on an unknown funnel_id. That is useful context but not a full behavioral picture for a destructive tool, so a 3 rather than the 4 this extra disclosure would otherwise earn.

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 action, then the confirmation rule, then the side-effect note. Nothing is padded and every clause carries a distinct fact.

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 three-parameter mutation with no output schema, the highest-risk facts — that it is destructive, that it previews by default, and that analytics data survives — are all present. The remaining gap is provenance of funnel_id and error behavior for a missing funnel, which keep it below a 5.

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 67%: site and confirm are already described in the schema, and the description only restates the confirm behavior rather than adding new syntax or constraints. funnel_id is the required parameter and is undocumented in both places, with no hint that it comes from list_funnels. Baseline 3 fits when the schema carries most of the burden.

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?

States a specific verb and resource ("Delete a funnel saved in the dashboard"), which cleanly separates it from delete_segment, delete_alert, and update_funnel in the sibling list. It stops short of explicitly naming those siblings, so an agent still relies on the resource noun alone to disambiguate.

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?

Gives a concrete operating rule: without confirm: true the tool only previews, so an agent knows the default call is a dry run and a real deletion requires a second, explicit invocation. It offers no guidance on alternatives such as list_funnels to obtain the id, or get_funnel to inspect before deleting.

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