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

With no annotations, the description carries the full burden and does so well: it discloses the 1 CRD cost per call, that the charge applies even to rejected calls, that a 429 RATE_LIMITED is free, and that error results carry a request_id to quote to support. This is exactly the behavioral context an agent needs before invoking a paid mutation.

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?

Dense but front-loaded: purpose first, then the credit_type_id branch, then update semantics, then cost/error behavior. Every sentence carries operational information with no filler.

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 paid mutation with no annotations and no output schema, the description covers cost, error handling, and update semantics thoroughly. It stops short of describing what a successful response contains, which is a minor gap given no output schema exists.

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 baseline is 3, but the description adds real meaning beyond the schema: the credit_type_id vs default-program distinction and the create-if-needed behavior, plus the partial-update rule that governs all optional fields.

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 pair (create or update) and resource (referral program) plus what the program contains (credits to referrer and referred user). It is clearly the write counterpart to get_referral_settings among the siblings.

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?

Explains the key branching condition: with credit_type_id it writes that credit type's program (creating if needed), without it the project default. It also clarifies partial-update semantics ('Only fields you pass change'). It does not explicitly name get_referral_settings as the read alternative, so not a 5.

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