subtract_customer

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

There are no annotations, so the description carries the full burden of explaining behavior. It does mention that sets are 'identified by primary keys and reloaded for this session,' which is a useful detail, but it does not state whether the operation mutates data, returns a new set, or what side effects might occur. The phrase 'reloaded for this session' is also vague and could confuse an agent about statefulness.

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 description is a single concise sentence with the core operation front-loaded. The phrase 'and reloaded for this session' adds some behavioral context but is somewhat awkward and not essential for initial identification. Overall it is appropriately short and well-structured.

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?

With no annotations and no output schema, the description is the only source of behavioral context. It does not describe the return value, whether the operation is read-only, or the exact semantics of 'subtract' in terms of primary keys. For a tool that takes two sets and computes a difference, an agent would need more context to call it confidently.

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 schema only says left and right are arrays of strings, with no descriptions property coverage. The description adds meaningful meaning by clarifying that the arrays represent Customer sets and that the string elements are primary keys. This is the essential semantic needed to invoke the tool correctly, though it does not explicitly explain the order-sensitivity of left and right.

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 names a specific operation ('subtract') and a specific resource ('Customer sets'), making the tool's purpose immediately clear. The sibling set-operation tools (union_customer, intersect_customer, aggregate_customer) are all distinguishable by the verb used. Even though it does not explicitly say 'left minus right', the meaning is clear enough from the verb and context.

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 word 'subtract' implies this is for set-difference operations, and the sibling names give contextual contrast with union/intersect tools. However, there is no explicit guidance on when to choose this tool versus alternatives, no examples, and no mention of when not to use it. The usage is implied rather than stated.

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