associate_email

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

With no annotations present, the description carries the burden well: it discloses that the email is never sent by the client and is instead extracted server-side from the verified idToken, and that computedData must come from buildAssociateEmailComputedData as a managed-custody payload. It stops short of covering idempotency/repeat-call behavior or what happens if an email is already associated.

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?

Four short sentences, front-loaded with the action and immediately followed by the sequencing rule. Slightly dense with parenthetical metadata (404/code 108, managed-custody), but every clause carries operational information.

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 two-parameter mutation with no annotations or output schema, the description supplies the critical prerequisite chain, the source of the payload, and the reason the email argument is absent. Missing only return-value and error-handling detail, which is a modest gap given no output schema exists.

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 description coverage is 100%, so the baseline is 3; the description goes slightly beyond by clarifying the negative case (no email parameter exists — the backend derives it) and by naming the specific builder function that must produce computedData. It does not expand on token format, expiry, or validation failure modes.

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 (link) and resource (the email claim from a Google ID token) tied to a concrete target (the caller's wallet). It is clearly distinguishable from the many trading/query siblings and from oauth_login, which it names directly.

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 ('Must be called before oauth_login when the wallet has no associated email yet') and even cites the failure signature (404/code 108) that selects this tool. It also names the alternative flow (oauth_login) and the ordering requirement, leaving nothing to inference.

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