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

With no annotations provided, the description carries the full burden and does so well: it discloses a per-call cost of 1 CRD charged even on rejection, that a 429 RATE_LIMITED is not charged, that errors return a request_id to quote to support, and that the payload can be null. These are exactly the operational traits an agent cannot get from the schema.

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?

Three sentences, front-loaded with what is returned, then parameter selection, then cost/error mechanics — each sentence adds distinct information with no restatement of the tool name or 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?

There is no output schema, and the description compensates by naming the returned fields and the null case, plus billing and error/request_id behavior. The return description is a field list rather than a full shape, so an agent still infers the envelope, but nothing needed to call the tool correctly is missing.

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, and the description earns an increment by explaining the semantics of credit_type_id — its default behavior when omitted and its null-result behavior — which the schema's one-line "Credit type whose program to read" does not convey. api_key, project_id, and x402_payment are left entirely to 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?

Opens with a specific verb+resource ("Get a referral program's settings") and enumerates the returned fields (is_active, referrer/referee credits, credit type), which clearly separates it from the mutating save_referral_settings sibling. It stops short of naming the sibling or list_referrals explicitly, so differentiation is implied by the verb rather than stated.

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?

Gives precise selection logic for the main discriminator: pass credit_type_id to read that credit type's program, omit it for the project's default program, and expect null settings when a credit type has no program. It does not contrast this tool with adjacent siblings (list_referrals, generate_referral_code), so tool-level routing is left to inference.

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