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

The description clearly discloses a mutating side effect ('MUTATES Autumn billing data') that goes beyond the generic destructiveHint, and it specifies the exact API endpoint. It does not cover every potential side effect (e.g. Stripe creation behavior), but it is direct about the core behavioral risk.

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?

Two short sentences deliver the key facts with zero filler, and the mutation warning is front-loaded. The API endpoint line is useful and not redundant.

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?

The tool has nine parameters and no output schema, yet the description explains only the core operation. It leaves the response shape and any additional side effects of parameters like create_in_stripe to be inferred rather than stated.

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 the input schema already documents every parameter. The description adds only the context that lookup is by id, which maps to customer_id, but it does not need to repeat the schema.

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 states a clear verb and resource: it 'fetches a customer by id' and 'creat[es] them if they do not exist.' This distinguishes it from read-only siblings like get_customer by explicitly flagging the creation side effect.

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 intended use is implied by 'creating them if they do not exist,' so an agent can infer this is for ensuring a customer exists before acting. However, it never explicitly names alternatives such as get_customer or states when not to use this tool.

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