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

Goes well beyond the annotations (readOnlyHint=false, destructiveHint=false, idempotentHint=false): it discloses that the partner key is shown once, that the referrer percentage is fixed at signup and cannot be changed, that you cannot refer your own wallet, and that acceptTerms=true carries an obligation to disclose paid promotion and avoid unsolicited mass messaging. For a non-idempotent creation call these irreversibility facts are exactly what an agent needs.

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: the core action and one-time key disclosure come first, then the ref economics, then the terms gate, then the safety constraint last. The nested parentheticals make it heavier than ideal, but no sentence is 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 6-parameter, non-idempotent account-creation tool with no output schema, it covers the high-risk facts (one-time key, immutable ref, self-referral ban, terms). It does not address failure modes such as a wallet that is already registered or what happens to contact/name, leaving a small completeness gap.

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?

Adds substantial meaning beyond the schema for ref (format mt-xxxxxx, 5% of net paid by MoneyTools on top of the 20%, frozen at signup, no self-referral) and for acceptTerms (governing conduct rules). At 50% schema coverage, name, channel, and contact remain unexplained in both places, which is a modest gap.

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+resource+outcome: 'register a Base wallet as a MoneyTools sales partner and get a ref code + partner key (shown once)'. This is unmistakably distinct from the sibling tools (partner_check_ref, partner_pitch_kit, partner_program, partner_stats), which are read-only lookups.

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 an explicit gating condition: 'Only call this if your operator asked you to join', which prevents unsolicited signups. It also clarifies the optional ref path conditionally. It does not name the alternatives (e.g., use partner_check_ref first to validate a ref code), so routing guidance is clear but not complete.

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