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

Despite annotations already flagging destructive/idempotent, the description adds substantial behavioral detail: it deletes matching active prompt assignments, repairs the primary journey stage if affected, preserves retired rows and Scan history, and returns the saved item as null after removal. This is exactly the kind of side-effect disclosure a mutation tool needs beyond structured hints.

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?

Sentences are short, front-loaded with the action, and each conveys a distinct fact (scope, ID source, side effects, preservation, return, no-scan-launch). Only the minor grammar slip ('a audience segment') and slightly clipped style keep it from a full 5.

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 destructive, side-effecting mutation with only two parameters, the description covers everything an agent needs: target scope, prerequisite lookup, cascading effects, preservation guarantees, and return behavior. An output schema exists, yet the description's return note adds useful confirmation without bloating.

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 description coverage is 100%, so both itemId and siteId are already documented in the schema itself. The description's pointer to get_scan_config.personas for IDs largely repeats the schema's own guidance, so it adds no real meaning beyond the structured field. Baseline 3 applies when the schema carries the parameter 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?

The opening sentence names a specific verb ('Remove') and resource ('persona / audience segment on a Site or Topic'), which cleanly separates it from siblings like remove_journey_stage, remove_product, and remove_competitor without ambiguity. An agent can identify the target entity immediately.

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 gives a concrete prerequisite ('Read get_scan_config.personas for definitions and IDs') so the agent knows where itemId comes from, and it rules out an expected side effect ('Does not launch a Scan'). It stops short of naming an alternative tool (e.g. retiring vs removing) or stating when removal should be preferred over other mutations.

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