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

Annotations only declare the generic safety profile (not read-only, not destructive, not idempotent); the description adds the consent gate, the return shape ('same view as kelpo_affiliate_program (link, next steps)') and the 409 conflict behavior with a retry alternative. That is meaningful context an agent could not infer from structured fields.

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?

Front-loaded with the action and its guardrail, and every clause carries information (consent, return shape, 409 recovery). The embedded JSON argument snippet is slightly clunky in prose but earns its place by showing the exact payload shape.

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 one-parameter mutation with no output schema, the description covers the consent prerequisite, the expected result by reference to a sibling's view, and the failure mode. Nothing needed to call it 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?

The nested JoinBody fields do carry their own descriptions in the schema, but the top-level body property has none, so the inline example {"body": {"code": "NORA", "accept_terms": true}} plus the 'code the person chose' framing genuinely adds value. It stops short of explaining code normalization or collision handling beyond the 409 note.

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 and resource ('Join the affiliate program') plus the required input ('with the code the person chose'). It is clearly distinguishable from kelpo_affiliate_program (viewing) and kelpo_update_affiliate_settings (settings mutation) named in the sibling list.

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 precondition ('only after you showed them the terms and they said yes') and an explicit prohibition ('never on their behalf'), plus the recovery path on failure ('409 when the code is taken: offer another one'). It also routes the agent to kelpo_affiliate_program for the terms text it must show first.

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