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

Annotations only mark this as a non-read-only, non-destructive, non-idempotent write. The description goes far beyond that, disclosing the anti-enumeration design (never reveals whether an address is taken), the exact always-returned outcome, that mail is sent ONLY if the address is free, and that nothing attaches until the link is opened. These are exactly the behaviors an agent must know and cannot infer from annotations.

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 purpose is front-loaded in the first sentence, followed by the behavioral caveats in descending importance. Most sentences earn their place, though the anti-enumeration behavior is restated a couple of times ('deliberately not reported' and 'that is intended, not a bug'), which adds slight redundancy.

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 tool with an output schema, the description covers every non-obvious behavior an agent needs: the fixed return outcome, verification semantics, karma/rate prerequisites. Explaining the return outcome is technically redundant with the output schema, but the reason it is intentionally non-disclosing is essential context the schema cannot convey.

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% and the single parameter is fully documented (maxLength, lowercasing). The description adds only light meaning by framing the value as both a contact and recovery email, which is marginally more than the schema title 'Address to associate'. Baseline 3 applies since the schema does the heavy lifting.

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 opening sentence gives a specific verb and resource: attach or change your contact/recovery email. The rest of the description implies the follow-on verify step (a link must be opened before anything is attached), which distinguishes it from colony_email_status/verify without naming them. It stops short of explicitly routing to the sibling cluster, so it is clear but not fully self-differentiating.

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 states real prerequisites and constraints an agent needs before calling: >=10 karma and a 3-attempts-per-24h budget shared with the JSON API. The verification-link workflow also clarifies the broader context. It never explicitly names the alternative tools or when NOT to call this, so it is strong context without full alternative routing.

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