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

The annotations already flag destructiveHint=true, but the description goes well beyond them by naming exactly what is destroyed: all signals, legacy categories and ICP filters. It also discloses the exception (unset custom SQL conditions persist, joined with AND), the preservedConditions field in the reply, and the paid-plan requirement.

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?

It is front-loaded with the create/replace distinction and every sentence carries information. Minor cost: 'Then the reply has preservedConditions, the number of these conditions' is wordy and could be tightened, and the preserved-conditions caveat is buried mid-paragraph.

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 mutation with a nested criteria object and no output schema, the description covers the mutation scope, the persistence exception, the plan gate, and the one return value that matters. An agent has everything needed to call it correctly or defer to previewSignalSet.

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 100% so the baseline is 3, but the description adds real meaning: setId switches the tool from create to replace semantics, name applies only to a new set, and criteria uses 'the same format as previewSignalSet', which points the agent at a concrete reference for a nested object the schema does not detail.

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 first sentence names a specific verb+resource pair and splits it into two modes: 'Create a signal set, or replace the criteria of an existing one.' The setId / no-setId split makes it immediately distinguishable from getSignalSet, listSignalSets, deleteSignalSet and previewSignalSet.

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 explicit routing: use previewSignalSet first to check the criteria match enough stores, and 'Paid plans only' as a hard prerequisite. The create-vs-update branch is spelled out, and the plan limit constraint on new sets is flagged.

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