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

The description discloses many behavioral traits: one inviter per organization, irreversibility, self-invitation refusal, the $3 bonus, retry behavior, and state recovery. However, it directly contradicts the annotation idempotentHint=false by stating that repeating the same invitation returns ALREADY_APPLIED and the same bonus, even after a lost answer. This is an annotation contradiction.

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 dense but every sentence and clause earns its place: invocation timing, prohibition on invented codes, invariants, bonus effect, retry semantics, and recovery path. It is front-loaded with the primary action and constraint, with no filler or repetition of schema content.

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 single-parameter tool with no output schema, the description is unusually complete: it covers when to call, constraints, side effects, repeated-call behavior, and how to recover state. The only flaw is the metadata contradiction, which is already penalized in behavioral transparency; the prose itself gives an agent everything needed to invoke the tool correctly.

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 schema already fully documents codeOrUrl. The description reinforces that it is the code or full invitation URL supplied by the developer and adds the condition to use it before first publication, but it does not add significant semantic detail beyond 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 uses a specific verb and resource: 'Apply a developer-provided referral code or invitation URL to this organization' before the first Sandbox publication. It clearly separates this from get_referral_program by positioning that tool as the state-recovery alternative.

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 explicitly states when to use the tool ('before its first-ever Sandbox publication'), what not to do ('Never invent a code'), who is refused ('self-invitations'), and how to disambiguate from the sibling get_referral_program after an uncertain result. This is strong guidance with both inclusion and exclusion criteria.

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